> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Neon MCP

> Manage Neon projects, branches, databases, and development workflows.

![Neon MCP logo](https://mintcdn.com/composio-preview/9YPuzjEU4UlMnwGq/images/toolkits/neon_mcp.svg?fit=max\&auto=format\&n=9YPuzjEU4UlMnwGq\&q=85\&s=6152a3db9f2914089060822f333ae7f2)

* **Category:** databases
* **Auth:** DCR\_OAUTH
* **Composio-managed OAuth available?** No
* **Tools:** 104
* **Triggers:** 0
* **Slug:** `NEON_MCP`
* **Version:** 20261018\_00

## Tools

> [accordion] Add auth oauth provider
>
> **Slug:** `NEON_MCP_ADD_AUTH_OAUTH_PROVIDER`
>
> Adds an OAuth provider configuration to the specified branch's Neon Auth integration.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **id** `string ("google" | "github" | "microsoft" | "vercel")` *required*
>
> **branch\_id** `string` *required*
>
> **client\_id** `string`
>
> **project\_id** `string` *required*
>
> **client\_secret** `string`
>
> **microsoft\_tenant\_id** `string`

> [accordion] Add auth trusted domain
>
> **Slug:** `NEON_MCP_ADD_AUTH_TRUSTED_DOMAIN`
>
> Adds a domain to the redirect URI whitelist for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **domain** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **auth\_provider** `string ("mock" | "stack" | "better_auth")` *required*

> [accordion] Compare database schema
>
> **Slug:** `NEON_MCP_COMPARE_DATABASE_SCHEMA`
>
> Compare one database's SQL schema on a branch to another. `database_name` is required. Omit `base_branch_id` to compare against the parent; it is a branch id (`br-...`), not a name. Pass `lsn`, `timestamp`, `base_lsn`, or `base_timestamp` only for a point-in-time comparison.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **lsn** `string`
>
> **base\_lsn** `string`
>
> **branch\_id** `string` *required*
>
> **timestamp** `string`
>
> **project\_id** `string` *required*
>
> **database\_name** `string` *required*
>
> **base\_branch\_id** `string`
>
> **base\_timestamp** `string`

> [accordion] Complete database migration
>
> **Slug:** `NEON_MCP_COMPLETE_DATABASE_MIGRATION`
>
> Apply or discard a prepared migration and delete the temporary branch. NEVER run autonomously; always ask the user first. Pass migration\_id, migration\_sql, database\_name, project\_id, temporary\_branch\_id, and parent\_branch\_id from prepare\_database\_migration. Set apply\_changes false to discard; omitting it applies the migration.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> The project ID. Pass the exact value from prepare\_database\_migration.
>
> **migration\_id** `string` *required*
>
> The migration ID from prepare\_database\_migration.
>
> **apply\_changes** `boolean`
>
> Whether to apply the migration. Set to false to just delete the temp branch without applying.
>
> **database\_name** `string` *required*
>
> The database name. Pass the exact value from prepare\_database\_migration.
>
> **migration\_sql** `string` *required*
>
> The SQL statements to apply. Pass the exact value from prepare\_database\_migration.
>
> **parent\_branch\_id** `string` *required*
>
> The parent branch ID where migration will be applied.
>
> **temporary\_branch\_id** `string` *required*
>
> The temporary branch ID to delete after migration.

> [accordion] Complete query tuning
>
> **Slug:** `NEON_MCP_COMPLETE_QUERY_TUNING`
>
> Apply or discard query-tuning changes and delete the temporary branch. NEVER run autonomously. Before calling, apply suggested SQL with run\_sql on the temporary branch and re-run explain\_sql\_statement. Pass the tuning\_id from prepare\_query\_tuning, not the branch id, plus temporary\_branch\_id. Set apply\_changes true to apply; omitting it discards. Call this even when the user rejects the changes. Do not use prepare\_database\_migration.
>
> #### Input Parameters
>
> **branch\_id** `string`
>
> The ID or name of the branch that receives the changes. If not provided, the default (main) branch will be used.
>
> **role\_name** `string`
>
> The name of the role to connect with. If you have used a specific role in prepare\_query\_tuning you MUST pass the same role again to this tool. If not provided, the default role (usually "neondb\_owner") will be used.
>
> **tuning\_id** `string` *required*
>
> The ID of the tuning to complete. This is NOT the branch ID. Remember this ID from the prior step using tool prepare\_query\_tuning.
>
> **project\_id** `string` *required*
>
> The ID of the project to execute the query against
>
> **apply\_changes** `boolean`
>
> Whether to apply the suggested changes to the main branch
>
> **database\_name** `string` *required*
>
> The name of the database to execute the query against
>
> **temporary\_branch\_id** `string` *required*
>
> The ID of the temporary branch that needs to be deleted after tuning.
>
> **suggested\_sql\_statements** `array` *required*
>
> The SQL DDL statements to execute to improve performance. These statements are the result of the prior steps, for example creating additional indexes.
>
> **should\_delete\_temporary\_branch** `boolean`
>
> Whether to delete the temporary branch after tuning

> [accordion] Create auth user
>
> **Slug:** `NEON_MCP_CREATE_AUTH_USER`
>
> Creates a new user in the Neon Auth user directory for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string`
>
> **email** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Create branch
>
> **Slug:** `NEON_MCP_CREATE_BRANCH`
>
> Creates a branch with a read-write compute and waits until it is ready. Pass `no_compute: true` to skip the endpoint. Does not return a connection string; call `get_connection_string` with the project and branch id. Copies the parent at HEAD; point-in-time restore is `restore_snapshot`.
>
> #### Input Parameters
>
> **name** `string`
>
> **compute** `object`
>
> **parent\_id** `string`
>
> **no\_compute** `boolean`
>
> Skip the read-write endpoint. Default false. Cannot be combined with compute.
>
> **project\_id** `string` *required*

> [accordion] Create postgres database
>
> **Slug:** `NEON_MCP_CREATE_POSTGRES_DATABASE`
>
> Creates a database in the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> **branch\_id** `string` *required*
>
> **owner\_name** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Create postgres endpoint
>
> **Slug:** `NEON_MCP_CREATE_POSTGRES_ENDPOINT`
>
> Creates a compute endpoint on a branch. Does not return a connection string; call `get_connection_string`.
>
> #### Input Parameters
>
> **name** `string`
>
> **type** `string ("read_only" | "read_write")` *required*
>
> **disabled** `boolean`
>
> **settings** `object`
>
> **branch\_id** `string` *required*
>
> **region\_id** `string`
>
> **project\_id** `string` *required*
>
> **pooler\_mode** `string ("transaction")`
>
> **provisioner** `string`
>
> **pooler\_enabled** `boolean`
>
> **passwordless\_access** `boolean`
>
> **suspend\_timeout\_seconds** `integer`
>
> **autoscaling\_limit\_max\_cu** `number`
>
> **autoscaling\_limit\_min\_cu** `number`

> [accordion] Create postgres role
>
> **Slug:** `NEON_MCP_CREATE_POSTGRES_ROLE`
>
> Creates a Postgres role in the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> **no\_login** `boolean`
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Create project
>
> **Slug:** `NEON_MCP_CREATE_PROJECT`
>
> Creates a Neon project and waits until the default compute is ready. Pass `org_id` with a personal API key. Does not return a connection string; call `get_connection_string` with the project id.
>
> #### Input Parameters
>
> **name** `string`
>
> **branch** `object`
>
> **org\_id** `string`
>
> **settings** `object`
>
> **region\_id** `string`
>
> **pg\_version** `integer`
>
> **provisioner** `string`
>
> **store\_passwords** `boolean`
>
> **autoscaling\_limit\_max\_cu** `number`
>
> **autoscaling\_limit\_min\_cu** `number`
>
> **default\_endpoint\_settings** `object`
>
> **history\_retention\_seconds** `integer`

> [accordion] Create snapshot
>
> **Slug:** `NEON_MCP_CREATE_SNAPSHOT`
>
> Creates a snapshot from the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **lsn** `string`
>
> **name** `string`
>
> **branch\_id** `string` *required*
>
> **timestamp** `string`
>
> **expires\_at** `string`
>
> **project\_id** `string` *required*

> [accordion] Create storage bucket
>
> **Slug:** `NEON_MCP_CREATE_STORAGE_BUCKET`
>
> Creates a new branchable object storage bucket on the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **access\_level** `string ("private" | "public_read")`

> [accordion] Delete auth oauth provider
>
> **Slug:** `NEON_MCP_DELETE_AUTH_OAUTH_PROVIDER`
>
> Deletes an OAuth provider from the specified project.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **oauth\_provider\_id** `string ("google" | "github" | "microsoft" | "vercel")` *required*

> [accordion] Delete auth trusted domain
>
> **Slug:** `NEON_MCP_DELETE_AUTH_TRUSTED_DOMAIN`
>
> Removes a domain from the redirect URI whitelist for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **domains** `array` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **auth\_provider** `string ("mock" | "stack" | "better_auth")` *required*

> [accordion] Delete auth user
>
> **Slug:** `NEON_MCP_DELETE_AUTH_USER`
>
> Deletes the specified user from the Neon Auth user directory for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **auth\_user\_id** `string` *required*

> [accordion] Delete branch
>
> **Slug:** `NEON_MCP_DELETE_BRANCH`
>
> Delete a branch and all its data. NEVER run autonomously; always ask the user first. For the whole project, use `delete_project`.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Delete data api
>
> **Slug:** `NEON_MCP_DELETE_DATA_API`
>
> Deletes the Neon Data API for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **database\_name** `string` *required*

> [accordion] Delete function
>
> **Slug:** `NEON_MCP_DELETE_FUNCTION`
>
> Deletes the function identified by its slug.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **slug** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Delete functions custom domain
>
> **Slug:** `NEON_MCP_DELETE_FUNCTIONS_CUSTOM_DOMAIN`
>
> Removes a custom domain registered on the branch and stops routing it.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **domain** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Delete postgres database
>
> **Slug:** `NEON_MCP_DELETE_POSTGRES_DATABASE`
>
> Deletes the specified database from the branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **database\_name** `string` *required*

> [accordion] Delete postgres endpoint
>
> **Slug:** `NEON_MCP_DELETE_POSTGRES_ENDPOINT`
>
> Deletes the specified compute endpoint.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> **endpoint\_id** `string` *required*

> [accordion] Delete postgres role
>
> **Slug:** `NEON_MCP_DELETE_POSTGRES_ROLE`
>
> Deletes the specified Postgres role from the branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **role\_name** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Delete project
>
> **Slug:** `NEON_MCP_DELETE_PROJECT`
>
> Delete a Neon project and all its data. NEVER run autonomously; always ask the user first. For a single branch, use `delete_branch`.
>
> #### Input Parameters
>
> **project\_id** `string` *required*

> [accordion] Delete snapshot
>
> **Slug:** `NEON_MCP_DELETE_SNAPSHOT`
>
> Deletes the specified snapshot.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> **snapshot\_id** `string` *required*

> [accordion] Delete storage bucket
>
> **Slug:** `NEON_MCP_DELETE_STORAGE_BUCKET`
>
> Deletes the named bucket from the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **bucket\_name** `string` *required*

> [accordion] Delete storage object
>
> **Slug:** `NEON_MCP_DELETE_STORAGE_OBJECT`
>
> Deletes the named object from the bucket on the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **object\_key** `string` *required*
>
> **project\_id** `string` *required*
>
> **bucket\_name** `string` *required*

> [accordion] Delete storage objects by prefix
>
> **Slug:** `NEON_MCP_DELETE_STORAGE_OBJECTS_BY_PREFIX`
>
> Soft-deletes every object on the specified branch whose key starts with `prefix`, in a single call.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **prefix** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **bucket\_name** `string` *required*

> [accordion] Deploy function
>
> **Slug:** `NEON_MCP_DEPLOY_FUNCTION`
>
> Creates a deployment for the function. Supply at least one of `zip`, `environment`, or `runtime`; omitted fields inherit the latest version. The first deployment must include `zip`.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **zip** `string`
>
> Base64-encoded binary file contents.
>
> **slug** `string` *required*
>
> **runtime** `string ("nodejs24")`
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **environment** `string`

> [accordion] Describe branch
>
> **Slug:** `NEON_MCP_DESCRIBE_BRANCH`
>
> Get a tree view of all objects in a branch, including databases, schemas, tables, views, and functions. Do not use when you only need table names (use `get_database_tables` instead) or column detail (use `describe_table_schema` instead).
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> An ID of the branch to describe
>
> **project\_id** `string` *required*
>
> The ID of the project
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.

> [accordion] Describe project
>
> **Slug:** `NEON_MCP_DESCRIBE_PROJECT`
>
> Retrieves the project record (settings, compute, usage). Call `list_branches` for branches.
>
> #### Input Parameters
>
> **project\_id** `string` *required*

> [accordion] Describe table schema
>
> **Slug:** `NEON_MCP_DESCRIBE_TABLE_SCHEMA`
>
> Get column definitions, data types, and constraints for a specific table. Do not use when you need all tables in a database (use `get_database_tables` instead).
>
> #### Input Parameters
>
> **branch\_id** `string`
>
> An optional ID of the branch to execute the query against. If not provided the default branch is used.
>
> **project\_id** `string` *required*
>
> The ID of the project to execute the query against
>
> **table\_name** `string` *required*
>
> The table name, optionally schema-qualified (for example, crm.contacts)
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.

> [accordion] Disable auth
>
> **Slug:** `NEON_MCP_DISABLE_AUTH`
>
> Disables the Neon Auth integration for the specified branch, removing the connection to the authentication provider.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **delete\_data** `boolean`

> [accordion] Explain sql statement
>
> **Slug:** `NEON_MCP_EXPLAIN_SQL_STATEMENT`
>
> Analyze the query execution plan for a SQL statement using EXPLAIN ANALYZE. Do not use when you need to execute the query for results (use `run_sql` instead).
>
> #### Input Parameters
>
> **sql** `string` *required*
>
> The SQL statement to analyze
>
> **analyze** `boolean`
>
> Whether to include ANALYZE in the EXPLAIN command
>
> **branch\_id** `string`
>
> An optional ID of the branch to execute the query against. If not provided the default branch is used.
>
> **project\_id** `string` *required*
>
> The ID of the project to execute the query against
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.

> [accordion] Fetch
>
> **Slug:** `NEON_MCP_FETCH`
>
> Fetch detailed information about a specific organization, project, or branch using the ID returned by the `search` tool.
>
> #### Input Parameters
>
> **id** `string` *required*
>
> The ID returned by the search tool to fetch detailed information about the entity

> [accordion] Finalize branch restore
>
> **Slug:** `NEON_MCP_FINALIZE_BRANCH_RESTORE`
>
> Finalize a branch created with `restore_snapshot` and `finalize: false`: reassign computes (this restarts them) and swap names so it replaces the original branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string`
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Get ai gateway
>
> **Slug:** `NEON_MCP_GET_AI_GATEWAY`
>
> Returns the AI Gateway endpoint host for the specified branch, used to render code-snippet base URLs.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Get auth
>
> **Slug:** `NEON_MCP_GET_AUTH`
>
> Retrieves the Neon Auth integration details for the specified branch, including the auth provider type and integration status.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Get branch
>
> **Slug:** `NEON_MCP_GET_BRANCH`
>
> Retrieves information about the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Get connection string
>
> **Slug:** `NEON_MCP_GET_CONNECTION_STRING`
>
> Get a PostgreSQL connection string for a Neon database. The branch must have a compute endpoint. `create_project` and `create_branch` do not return one; call this after they succeed. All parameters are optional; the tool resolves the project, branch, and database automatically if not specified. Requires write access: the connection string carries a privileged role password, so it is unavailable in read-only mode. A read-only caller who needs a DATABASE\_URL must copy it from [https://console.neon.tech](https://console.neon.tech) manually.
>
> #### Input Parameters
>
> **branch\_id** `string`
>
> The ID or name of the branch. If not provided, the default branch will be used.
>
> **role\_name** `string`
>
> The name of the role to connect with. If not provided, the database owner name will be used.
>
> **compute\_id** `string`
>
> The ID of the compute/endpoint. If not provided, the read-write compute associated with the branch will be used.
>
> **project\_id** `string` *required*
>
> The ID of the project. If not provided, the only available project will be used.
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.

> [accordion] Get data api
>
> **Slug:** `NEON_MCP_GET_DATA_API`
>
> Retrieves the Neon Data API configuration for the specified branch, including endpoint URL, enabled state, and database settings.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **database\_name** `string` *required*

> [accordion] Get database tables
>
> **Slug:** `NEON_MCP_GET_DATABASE_TABLES`
>
> List all tables in a Neon database. Do not use when you need column-level detail for a specific table (use `describe_table_schema` instead).
>
> #### Input Parameters
>
> **branch\_id** `string`
>
> An optional ID of the branch. If not provided the default branch is used.
>
> **project\_id** `string` *required*
>
> The ID of the project
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.

> [accordion] Get default branch
>
> **Slug:** `NEON_MCP_GET_DEFAULT_BRANCH`
>
> Resolve the project's default branch by the default flag, not by name.
>
> #### Input Parameters
>
> **project\_id** `string` *required*

> [accordion] Get doc resource
>
> **Slug:** `NEON_MCP_GET_DOC_RESOURCE`
>
> Fetch one Neon documentation page as markdown. Pass a slug from list\_docs\_resources (for example docs/guides/prisma.md).
>
> #### Input Parameters
>
> **slug** `string` *required*
>
> The docs page slug (path) to fetch, e.g. 'docs/guides/prisma.md'. Slugs use .md file endings matching the URLs in the documentation index. Use the list\_docs\_resources tool first to discover available slugs.

> [accordion] Get function
>
> **Slug:** `NEON_MCP_GET_FUNCTION`
>
> Returns the function identified by its slug.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **slug** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Get neon auth config
>
> **Slug:** `NEON_MCP_GET_NEON_AUTH_CONFIG`
>
> Read Neon Auth config for a branch with OAuth and SMTP secrets redacted as "***redacted***". Requires provision\_neon\_auth first.
>
> #### Input Parameters
>
> **branch\_id** `string`
>
> Branch ID. If omitted, the project default branch is used (same as provision\_neon\_auth).
>
> **project\_id** `string` *required*
>
> Neon project ID

> [accordion] Get operation
>
> **Slug:** `NEON_MCP_GET_OPERATION`
>
> Retrieves details for the specified operation.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> **operation\_id** `string` *required*

> [accordion] Get postgres database
>
> **Slug:** `NEON_MCP_GET_POSTGRES_DATABASE`
>
> Retrieves information about the specified database.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **database\_name** `string` *required*

> [accordion] Get postgres endpoint
>
> **Slug:** `NEON_MCP_GET_POSTGRES_ENDPOINT`
>
> Retrieves information about the specified compute endpoint.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> **endpoint\_id** `string` *required*

> [accordion] Get postgres role
>
> **Slug:** `NEON_MCP_GET_POSTGRES_ROLE`
>
> Retrieves details about the specified role.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **role\_name** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Get snapshot schedule
>
> **Slug:** `NEON_MCP_GET_SNAPSHOT_SCHEDULE`
>
> Returns the backup schedule for the specified branch, including the configured snapshot frequencies.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Get storage
>
> **Slug:** `NEON_MCP_GET_STORAGE`
>
> Returns whether branchable object storage is usable for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Inspect database
>
> **Slug:** `NEON_MCP_INSPECT_DATABASE`
>
> Run one read-only neon inspect db check (pick `check` from the input schema). Not for arbitrary SQL (`run_sql`), one statement's plan (`explain_sql_statement`), or applying indexes (`prepare_query_tuning`). Omit `database_name` to cover every database; some checks are compute-wide. If a check needs an extension, the tool names `CREATE EXTENSION`; ask before running it.
>
> #### Input Parameters
>
> **check** `string ("table-sizes" | "index-sizes" | "unused-indexes" | "seq-scans" | "long-running-queries" | "stalled-queries" | "locks" | "outliers" | "calls" | "lfc-hit-rate" | "working-set" | "vacuum-stats" | "bloat" | "replication-slots" | "subscriptions")` *required*
>
> Which diagnostic to run: `table-sizes`: Size of each table (including TOAST), largest first (pg\_table\_size) `index-sizes`: Size of each index, largest first (pg\_relation\_size) `unused-indexes`: Non-unique indexes with fewer than 50 scans — candidates for removal (pg\_stat\_user\_indexes) `seq-scans`: Number of sequential scans recorded against each table (pg\_stat\_user\_tables) `long-running-queries`: Queries running longer than 5 minutes (pg\_stat\_activity) `stalled-queries`: Active queries running longer than 30 seconds with parallel-worker grouping, waits, and blockers, oldest query group first (compute-wide) `locks`: Locks held with the acquiring query and its age (pg\_locks + pg\_stat\_activity) `outliers`: The 25 queries with the highest cumulative execution time since statistics were last reset (needs pg\_stat\_statements) `calls`: The 25 most frequently executed queries since statistics were last reset (needs pg\_stat\_statements) `lfc-hit-rate`: Local File Cache hit rate (compute-wide, needs neon extension) `working-set`: Estimated working set vs LFC size (compute-wide, needs neon extension) `vacuum-stats`: Autovacuum status per table: last (auto)vacuum, dead tuples, threshold `bloat`: Estimated bloat for the 25 most bloated tables (statistical estimate, no extension needed) `replication-slots`: Replication slots (compute-wide): kind, status, client, restart/confirmed-flush LSNs, and lag (pg\_replication\_slots + pg\_stat\_replication) `subscriptions`: Per-table logical replication progress on this subscriber (pg\_subscription\_rel)
>
> **limit** `integer`
>
> Maximum number of rows to return from the combined result. Per-database ranking and SQL caps are applied first. The response reports how many rows the check produced and whether they were truncated, so raise this only when `truncated` is true. A few checks are capped in SQL and say so in their description.
>
> **branch\_id** `string`
>
> An optional ID of the branch. If not provided the default branch is used.
>
> **compute\_id** `string`
>
> The ID of the compute/endpoint. If not provided, the read-write compute associated with the branch will be used.
>
> **project\_id** `string` *required*
>
> The ID of the project to inspect
>
> **database\_name** `string`
>
> For a database-scoped check, the database to inspect. Omit to cover every database on the branch. Ranking and SQL row limits stay per database. One failing database fails the whole run. For a compute-wide check, the database to connect through; the check still runs once for the whole compute and the result does not include `databaseName`. The response `limit` applies to the combined rows after that.

> [accordion] List auth oauth providers
>
> **Slug:** `NEON_MCP_LIST_AUTH_OAUTH_PROVIDERS`
>
> Lists the OAuth providers configured for the specified branch's Neon Auth integration.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List auth trusted domains
>
> **Slug:** `NEON_MCP_LIST_AUTH_TRUSTED_DOMAINS`
>
> Lists the trusted domains in the redirect URI whitelist for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List branch computes
>
> **Slug:** `NEON_MCP_LIST_BRANCH_COMPUTES`
>
> Retrieves a list of compute endpoints for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List branches
>
> **Slug:** `NEON_MCP_LIST_BRANCHES`
>
> Retrieves a list of branches for the specified project. Returns every page. Pass limit to cap how many.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **search** `string`
>
> **sort\_by** `string ("name" | "created_at" | "updated_at")`
>
> **project\_id** `string` *required*
>
> **sort\_order** `string ("asc" | "desc")`
>
> **include\_deleted** `boolean`

> [accordion] List docs resources
>
> **Slug:** `NEON_MCP_LIST_DOCS_RESOURCES`
>
> List Neon documentation page slugs from neon.com/docs/llms.txt. Call this before get\_doc\_resource; do not guess slugs.

> [accordion] List functions
>
> **Slug:** `NEON_MCP_LIST_FUNCTIONS`
>
> Lists functions on the specified branch. Returns every page. Pass limit to cap how many.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List functions custom domains
>
> **Slug:** `NEON_MCP_LIST_FUNCTIONS_CUSTOM_DOMAINS`
>
> Lists all custom domains registered on the branch, across every target entity. Returns every page. Pass limit to cap how many.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List log fields
>
> **Slug:** `NEON_MCP_LIST_LOG_FIELDS`
>
> Lists the low-cardinality log fields observed on this branch. Call `list_log_field_values` with `field_name` to list distinct values.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List log field values
>
> **Slug:** `NEON_MCP_LIST_LOG_FIELD_VALUES`
>
> Lists distinct values for a low-cardinality log field. Call `list_log_fields` first for `field_name`; a field the branch has never emitted returns `unknown_field`. Pass `since` or `start_time`, not both; default is the previous six hours, max seven days. Private beta.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **since** `string`
>
> **source** `string ("function" | "storage" | "pg_endpoint")`
>
> **end\_time** `string`
>
> **branch\_id** `string` *required*
>
> **field\_name** `string` *required*
>
> **project\_id** `string` *required*
>
> **start\_time** `string`

> [accordion] List operations
>
> **Slug:** `NEON_MCP_LIST_OPERATIONS`
>
> Lists operations for a project. Omitting `limit` returns every remaining page. There is no `cursor` argument.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **project\_id** `string` *required*

> [accordion] List organizations
>
> **Slug:** `NEON_MCP_LIST_ORGANIZATIONS`
>
> List all organizations the current user belongs to. Supports optional `search` parameter to filter by name or ID.
>
> #### Input Parameters
>
> **search** `string`
>
> Search organizations by name or ID. You can specify partial name or ID values to filter results.

> [accordion] List postgres databases
>
> **Slug:** `NEON_MCP_LIST_POSTGRES_DATABASES`
>
> Retrieves a list of databases for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List postgres endpoints
>
> **Slug:** `NEON_MCP_LIST_POSTGRES_ENDPOINTS`
>
> Retrieves a list of compute endpoints for the specified project.
>
> #### Input Parameters
>
> **project\_id** `string` *required*

> [accordion] List postgres roles
>
> **Slug:** `NEON_MCP_LIST_POSTGRES_ROLES`
>
> Retrieves a list of Postgres roles from the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List project members
>
> **Slug:** `NEON_MCP_LIST_PROJECT_MEMBERS`
>
> Lists organization members and their per-project roles for an org-owned project. Returns every page. Pass limit to cap how many.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **project\_id** `string` *required*

> [accordion] List project permissions
>
> **Slug:** `NEON_MCP_LIST_PROJECT_PERMISSIONS`
>
> Retrieves details about users who have access to the project, including the permission `id`, the granted-to email address, and the date project access was granted.
>
> #### Input Parameters
>
> **project\_id** `string` *required*

> [accordion] List projects
>
> **Slug:** `NEON_MCP_LIST_PROJECTS`
>
> List Neon projects you own. Returns every page. Pass limit to cap how many. There is no `cursor` argument. Pass `org_id` with a personal API key to list that org's projects.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **org\_id** `string`
>
> **search** `string`
>
> **timeout** `integer`
>
> **recoverable** `boolean`

> [accordion] List regions
>
> **Slug:** `NEON_MCP_LIST_REGIONS`
>
> Lists Neon regions available to the authenticated account.

> [accordion] List slow queries
>
> **Slug:** `NEON_MCP_LIST_SLOW_QUERIES`
>
> List queries from pg\_stat\_statements by execution time, slowest first. For sizes, indexes, locks, cache, bloat, or replication use inspect\_database.
>
> #### Input Parameters
>
> **limit** `number`
>
> Maximum number of slow queries to return
>
> **branch\_id** `string`
>
> An optional ID of the branch. If not provided the default branch is used.
>
> **compute\_id** `string`
>
> The ID of the compute/endpoint. If not provided, the read-write compute associated with the branch will be used.
>
> **project\_id** `string` *required*
>
> The ID of the project to list slow queries from
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.
>
> **min\_execution\_time** `number`
>
> Minimum execution time in milliseconds to consider a query as slow

> [accordion] List snapshots
>
> **Slug:** `NEON_MCP_LIST_SNAPSHOTS`
>
> Lists the snapshots for the specified project.
>
> #### Input Parameters
>
> **project\_id** `string` *required*

> [accordion] List storage buckets
>
> **Slug:** `NEON_MCP_LIST_STORAGE_BUCKETS`
>
> Lists branchable object storage buckets visible on the specified branch, including those inherited from ancestor branches.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] List storage objects
>
> **Slug:** `NEON_MCP_LIST_STORAGE_OBJECTS`
>
> Lists objects visible in the named bucket on the specified branch, including those inherited from ancestor branches. Returns every page. Pass limit to cap how many.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **prefix** `string`
>
> **branch\_id** `string` *required*
>
> **delimiter** `string`
>
> **project\_id** `string` *required*
>
> **bucket\_name** `string` *required*

> [accordion] Prepare database migration
>
> **Slug:** `NEON_MCP_PREPARE_DATABASE_MIGRATION`
>
> Apply a schema change on a temporary branch and return a migration\_id. Test with run\_sql on that branch, ask the user, then complete\_database\_migration — even if they reject, so the temporary branch is deleted. Pass every field from the prepare response.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> The ID of the project to execute the query against
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.
>
> **migration\_sql** `string` *required*
>
> The SQL to execute to create the migration

> [accordion] Prepare query tuning
>
> **Slug:** `NEON_MCP_PREPARE_QUERY_TUNING`
>
> Analyze a slow query on a temporary branch and return a tuning\_id. Apply suggested SQL with run\_sql on that branch, re-run explain\_sql\_statement there, then complete\_query\_tuning with the tuning\_id (not the branch id) — apply\_changes true if they accept, omit it or pass false if they reject, so the temporary branch is deleted. Do not use prepare\_database\_migration.
>
> #### Input Parameters
>
> **sql** `string` *required*
>
> The SQL statement to analyze and tune
>
> **role\_name** `string`
>
> The name of the role to connect with. If not provided, the default role (usually "neondb\_owner") will be used.
>
> **project\_id** `string` *required*
>
> The ID of the project to execute the query against
>
> **database\_name** `string` *required*
>
> The name of the database to execute the query against

> [accordion] Presign storage object
>
> **Slug:** `NEON_MCP_PRESIGN_STORAGE_OBJECT`
>
> Returns a presigned URL that transfers bytes directly to or from the object's bucket on the specified branch, without the caller ever handling S3 credentials.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **operation** `string ("upload" | "download")` *required*
>
> **object\_key** `string` *required*
>
> **project\_id** `string` *required*
>
> **bucket\_name** `string` *required*
>
> **content\_type** `string`
>
> **expires\_in\_seconds** `integer`

> [accordion] Provision neon auth
>
> **Slug:** `NEON_MCP_PROVISION_NEON_AUTH`
>
> Enables Neon Auth for the specified branch by connecting it to an authentication provider.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **auth\_provider** `string ("mock" | "stack" | "better_auth")` *required*
>
> **database\_name** `string`

> [accordion] Provision neon data api
>
> **Slug:** `NEON_MCP_PROVISION_NEON_DATA_API`
>
> Creates a new instance of Neon Data API in the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **jwks\_url** `string`
>
> **settings** `object`
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **jwt\_audience** `string`
>
> **auth\_provider** `string ("neon_auth" | "external")`
>
> **database\_name** `string` *required*
>
> **provider\_name** `string`
>
> **skip\_auth\_schema** `boolean`
>
> **add\_default\_grants** `boolean`

> [accordion] Query logs
>
> **Slug:** `NEON_MCP_QUERY_LOGS`
>
> Returns logs for a branch. Pass `limit` to cap how many. There is no `cursor` argument. Filters combine with AND. Pass `logql` instead of structured filters, not with them. Give the window as `since` or `start_time`, not both; default is the previous hour, max seven days; `end_time` is exclusive. Private beta; a branch without logs access returns HTTP 404 with reason "telemetry\_not\_enabled".
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **limit** `integer`
>
> **logql** `string`
>
> **since** `string`
>
> **source** `string ("function" | "storage" | "pg_endpoint")`
>
> **end\_time** `string`
>
> **trace\_id** `string`
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **scope\_name** `string`
>
> **sort\_order** `string ("asc" | "desc")`
>
> **start\_time** `string`
>
> **service\_name** `string`
>
> **body\_contains** `string`
>
> **severity\_text** `string`
>
> **minimum\_severity** `string ("trace" | "debug" | "info" | "warn" | "error" | "fatal")`

> [accordion] Recover project
>
> **Slug:** `NEON_MCP_RECOVER_PROJECT`
>
> Recovers a deleted project within the 7-day deletion recovery period.
>
> #### Input Parameters
>
> **project\_id** `string` *required*

> [accordion] Register functions custom domain
>
> **Slug:** `NEON_MCP_REGISTER_FUNCTIONS_CUSTOM_DOMAIN`
>
> Registers a hostname on the branch and routes it to a function. Pass `entity_type: "function"` and `entity_id` as the slug from `list_functions`. Point a CNAME at the returned `cname_target`.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **domain** `string` *required*
>
> **branch\_id** `string` *required*
>
> **entity\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **entity\_type** `string` *required*

> [accordion] Reset from parent
>
> **Slug:** `NEON_MCP_RESET_FROM_PARENT`
>
> Reset a branch to its parent's current HEAD. Discards every change the branch has written since it diverged. NEVER run autonomously; always ask the user first. `preserve_under_name` saves the current state first and is required when the branch has children; those children move to the new branch. Point-in-time restore is `restore_snapshot`.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **preserve\_under\_name** `string`
>
> Name under which to save the current branch before the reset. Required when the branch has children; those children move to the new branch.

> [accordion] Reset postgres role password
>
> **Slug:** `NEON_MCP_RESET_POSTGRES_ROLE_PASSWORD`
>
> Resets the password for the specified Postgres role.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **role\_name** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Restart postgres endpoint
>
> **Slug:** `NEON_MCP_RESTART_POSTGRES_ENDPOINT`
>
> Restarts the specified compute endpoint by immediately suspending it and then starting it again.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> **endpoint\_id** `string` *required*

> [accordion] Restore snapshot
>
> **Slug:** `NEON_MCP_RESTORE_SNAPSHOT`
>
> Restore a snapshot onto a new or existing branch. The call waits until the branch is ready. Pass `target_branch_id` to restore onto an existing branch; omit it to create one. Pass `finalize: false` then call `finalize_branch_restore` to swap names later.
>
> #### Input Parameters
>
> **name** `string`
>
> **finalize** `boolean`
>
> Finalize immediately (move computes onto the restored branch). Defaults to true when restoring as a new branch and false when restoring onto an existing branch.
>
> **project\_id** `string` *required*
>
> **snapshot\_id** `string` *required*
>
> **target\_branch\_id** `string`

> [accordion] Run sql
>
> **Slug:** `NEON_MCP_RUN_SQL`
>
> Execute one SQL statement on a Neon database. If a prior step created a temporary branch, pass that branch\_id. NEVER run destructive SQL autonomously; always ask the user first.
>
> #### Input Parameters
>
> **sql** `string` *required*
>
> The SQL query to execute
>
> **branch\_id** `string`
>
> An optional ID of the branch to execute the query against. If not provided the default branch is used.
>
> **project\_id** `string` *required*
>
> The ID of the project to execute the query against
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.

> [accordion] Run sql transaction
>
> **Slug:** `NEON_MCP_RUN_SQL_TRANSACTION`
>
> Execute multiple SQL statements as one transaction. If a prior step created a temporary branch, pass that branch\_id. NEVER run destructive SQL autonomously; always ask the user first.
>
> #### Input Parameters
>
> **branch\_id** `string`
>
> An optional ID of the branch to execute the query against. If not provided the default branch is used.
>
> **project\_id** `string` *required*
>
> The ID of the project to execute the query against
>
> **database\_name** `string`
>
> The name of the database. If not provided, the default neondb or first available database is used.
>
> **sql\_statements** `array` *required*
>
> The SQL statements to execute

> [accordion] Search
>
> **Slug:** `NEON_MCP_SEARCH`
>
> Search across all organizations, projects, and branches by keyword. Returns matching items with id, title, and URL. Query must be at least 3 characters. Do not use when you need all projects (use `list_projects` instead).
>
> #### Input Parameters
>
> **query** `string` *required*
>
> The search query to find matching organizations, projects, or branches

> [accordion] Set default branch
>
> **Slug:** `NEON_MCP_SET_DEFAULT_BRANCH`
>
> Sets the specified branch as the project's default branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Set snapshot schedule
>
> **Slug:** `NEON_MCP_SET_SNAPSHOT_SCHEDULE`
>
> Replace a branch's automatic snapshot schedule. Frequency must be daily, weekly, or monthly.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **schedule** `array` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Start postgres endpoint
>
> **Slug:** `NEON_MCP_START_POSTGRES_ENDPOINT`
>
> Starts a compute endpoint.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> **endpoint\_id** `string` *required*

> [accordion] Suspend postgres endpoint
>
> **Slug:** `NEON_MCP_SUSPEND_POSTGRES_ENDPOINT`
>
> Suspends the specified compute endpoint.
>
> #### Input Parameters
>
> **project\_id** `string` *required*
>
> **endpoint\_id** `string` *required*

> [accordion] Update auth config
>
> **Slug:** `NEON_MCP_UPDATE_AUTH_CONFIG`
>
> Updates the auth configuration for the branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Update auth oauth provider
>
> **Slug:** `NEON_MCP_UPDATE_AUTH_OAUTH_PROVIDER`
>
> Updates an OAuth provider for the specified project.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **client\_id** `string`
>
> **project\_id** `string` *required*
>
> **client\_secret** `string`
>
> **oauth\_provider\_id** `string ("google" | "github" | "microsoft" | "vercel")` *required*
>
> **microsoft\_tenant\_id** `string`

> [accordion] Update auth user role
>
> **Slug:** `NEON_MCP_UPDATE_AUTH_USER_ROLE`
>
> Updates the role of a user in the Neon Auth user directory for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **roles** `array` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*
>
> **auth\_user\_id** `string` *required*

> [accordion] Update branch
>
> **Slug:** `NEON_MCP_UPDATE_BRANCH`
>
> Updates the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string`
>
> **branch\_id** `string` *required*
>
> **protected** `boolean`
>
> **expires\_at** `string`
>
> **project\_id** `string` *required*

> [accordion] Update data api
>
> **Slug:** `NEON_MCP_UPDATE_DATA_API`
>
> Updates the Neon Data API configuration for the specified branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **branch\_id** `string` *required*
>
> **db\_schemas** `array`
>
> **project\_id** `string` *required*
>
> **db\_max\_rows** `integer`
>
> **db\_anon\_role** `string`
>
> **openapi\_mode** `string`
>
> **database\_name** `string` *required*
>
> **jwt\_role\_claim\_key** `string`
>
> **db\_extra\_search\_path** `string`
>
> **db\_aggregates\_enabled** `boolean`
>
> **server\_timing\_enabled** `boolean`
>
> **jwt\_cache\_max\_lifetime** `integer`
>
> **server\_cors\_allowed\_origins** `string`

> [accordion] Update function
>
> **Slug:** `NEON_MCP_UPDATE_FUNCTION`
>
> Updates the function's mutable metadata — currently only the display `name`.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> **slug** `string` *required*
>
> **branch\_id** `string` *required*
>
> **project\_id** `string` *required*

> [accordion] Update postgres database
>
> **Slug:** `NEON_MCP_UPDATE_POSTGRES_DATABASE`
>
> Updates the specified database in the branch.
>
> branch\_id is a branch id (br-...), not a branch name. Call list\_branches to resolve a name.
>
> #### Input Parameters
>
> **name** `string`
>
> **branch\_id** `string` *required*
>
> **owner\_name** `string`
>
> **project\_id** `string` *required*
>
> **database\_name** `string` *required*

> [accordion] Update postgres endpoint
>
> **Slug:** `NEON_MCP_UPDATE_POSTGRES_ENDPOINT`
>
> Updates the specified compute endpoint.
>
> #### Input Parameters
>
> **name** `string`
>
> **disabled** `boolean`
>
> **settings** `object`
>
> **branch\_id** `string`
>
> **project\_id** `string` *required*
>
> **endpoint\_id** `string` *required*
>
> **pooler\_mode** `string ("transaction")`
>
> **provisioner** `string`
>
> **pooler\_enabled** `boolean`
>
> **passwordless\_access** `boolean`
>
> **suspend\_timeout\_seconds** `integer`
>
> **autoscaling\_limit\_max\_cu** `number`
>
> **autoscaling\_limit\_min\_cu** `number`

> [accordion] Update project
>
> **Slug:** `NEON_MCP_UPDATE_PROJECT`
>
> Updates the specified project.
>
> #### Input Parameters
>
> **name** `string`
>
> **settings** `object`
>
> **project\_id** `string` *required*
>
> **default\_endpoint\_settings** `object`
>
> **history\_retention\_seconds** `integer`

> [accordion] Update snapshot
>
> **Slug:** `NEON_MCP_UPDATE_SNAPSHOT`
>
> Updates the specified snapshot.
>
> #### Input Parameters
>
> **name** `string`
>
> **expires\_at** `string`
>
> **project\_id** `string` *required*
>
> **snapshot\_id** `string` *required*
