> ## 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.

# Memelord MCP

> Search meme templates, generate and edit image and video memes, upload media, and use Jester through Memelord’s hosted MCP server. Generation and editing tools spend the connected account’s usage balance; discovery, uploads, job status, and account information are free.

![Memelord MCP logo](https://mintcdn.com/composio-preview/ufpARLIsio16odJB/images/toolkits/memelord_mcp.svg?fit=max\&auto=format\&n=ufpARLIsio16odJB\&q=85\&s=f393e40bc0e8ff234715cca7463ed2ae)

* **Category:** model context protocol
* **Auth:** DCR\_OAUTH, API\_KEY
* **Composio-managed OAuth available?** No
* **Tools:** 19
* **Triggers:** 0
* **Slug:** `MEMELORD_MCP`
* **Version:** 00000000\_00

## Tools

> [accordion] Check video status
>
> **Slug:** `MEMELORD_MCP_CHECK_VIDEO_STATUS`
>
> Check one video job from any video-producing tool. Returns status (pending / processing → completed | failed) and the MP4 download URL once complete. Free — poll every few seconds after a tool returns a job\_id.
>
> #### Input Parameters
>
> **job\_id** `string` *required*
>
> job\_id returned by a video tool (e.g. generate\_video\_meme, edit\_video\_meme, run\_agent) or list\_video\_jobs

> [accordion] Create media upload url
>
> **Slug:** `MEMELORD_MCP_CREATE_MEDIA_UPLOAD_URL`
>
> Start a direct upload for a file too large to send inline (over 3 MB), typically a video. Returns an upload\_url and upload\_id: PUT the raw file bytes to upload\_url with the returned Content-Type header (for example curl -X PUT -H "Content-Type: video/mp4" --data-binary @clip.mp4 "\<upload\_url>"), then call upload\_media with upload\_id to get the file's url. The upload\_url expires after 2 hours. Accepts image/jpeg, image/png, image/webp, video/mp4, video/quicktime, video/webm; images up to 10 MB, videos up to 100 MB. Free.
>
> #### Input Parameters
>
> **size\_bytes** `integer`
>
> File size in bytes, to fail fast when it is over the limit
>
> **content\_type** `string` *required*
>
> MIME type of the file: image/jpeg, image/png, image/webp, video/mp4, video/quicktime, video/webm

> [accordion] Edit meme
>
> **Slug:** `MEMELORD_MCP_EDIT_MEME`
>
> Change the text of an image meme you already generated. Pass the edit\_handle from a generate\_caption\_meme / generate\_ai\_meme (or previous edit\_meme) result together with a plain-language instruction; use the slot numbers from that result's caption\_slots as target\_index to change just one box. Re-renders the image and returns a fresh URL, the updated caption\_slots, and a new edit\_handle (earlier handles stay valid, so you can branch from any version). Handles only work for the account that created them. Billed against your usage balance.
>
> #### Input Parameters
>
> **edit\_handle** `string` *required*
>
> edit\_handle from the generate\_caption\_meme, generate\_ai\_meme, or edit\_meme result being edited
>
> **instruction** `string` *required*
>
> What to change, e.g. "make the bottom text about JavaScript instead"
>
> **target\_index** `integer`
>
> slot number (from caption\_slots) of the one text box to change. Omit to let the editor decide.

> [accordion] Edit video meme
>
> **Slug:** `MEMELORD_MCP_EDIT_VIDEO_MEME`
>
> Rewrite the caption of a video meme and re-render it. Provide the template\_id and the current caption from a previous generate\_video\_meme job plus a plain-language instruction. Starts a new render job — poll check\_video\_status for the MP4. Billed against your usage balance.
>
> #### Input Parameters
>
> **caption** `string` *required*
>
> Current caption text to edit
>
> **instruction** `string` *required*
>
> What to change about the caption
>
> **template\_id** `string` *required*
>
> Video template asset id
>
> **force\_caption\_style** `string ("top" | "tiktok")`
>
> Force caption style: "top" (letterbox) or "tiktok" (centered overlay)

> [accordion] Generate ai meme
>
> **Slug:** `MEMELORD_MCP_GENERATE_AI_MEME`
>
> AI-remixed image memes: Jester picks a meme template (or uses template\_id), AI-edits the picture itself to fit the joke — swapping subjects, adding objects, or painting in people and products from reference\_image\_urls — then captions it. Use generate\_caption\_meme instead when you only want new text on an unchanged classic template. Returns signed image URLs plus template\_id, caption\_slots, and an edit\_handle for edit\_meme. Billed against your usage balance.
>
> #### Input Parameters
>
> **count** `integer`
>
> Number of memes to generate (default 1, max 10)
>
> **prompt** `string` *required*
>
> Topic, idea, or joke premise for the meme
>
> **category** `string ("trending" | "classic")`
>
> Restrict template selection to the trending pool or the classics pool (default: both)
>
> **template\_id** `string`
>
> Pin a specific image template asset id (from search\_memes / get\_trending\_memes)
>
> **include\_nsfw** `boolean`
>
> Allow NSFW-tagged templates (default true)
>
> **include\_political** `boolean`
>
> Allow political-tagged templates (default true)
>
> **reference\_image\_urls** `array`
>
> Up to 3 public image URLs (a person, product, logo, or style) for the AI edit to paint into the template; upload local files with upload\_media first

> [accordion] Generate caption meme
>
> **Slug:** `MEMELORD_MCP_GENERATE_CAPTION_MEME`
>
> Classic caption memes: Jester picks a real meme template from the library (or uses template\_id), writes new text for its caption slots, and renders that text on the unchanged template image. The picture is never AI-edited or repainted — use generate\_ai\_meme for that. Returns signed image URLs plus template\_id, caption\_slots, and an edit\_handle you can hand to edit\_meme to change the wording. Use search\_memes or get\_trending\_memes first if you want to pick the template yourself. Billed against your usage balance.
>
> #### Input Parameters
>
> **count** `integer`
>
> Number of memes to generate (default 1, max 10)
>
> **prompt** `string` *required*
>
> Topic, idea, or joke premise for the meme
>
> **category** `string ("classic" | "trending")`
>
> Template pool: "classic" (default) draws from classic templates that have real caption slots; "trending" draws from current trending templates
>
> **template\_id** `string`
>
> Pin a specific image template asset id (from search\_memes / get\_trending\_memes)
>
> **include\_nsfw** `boolean`
>
> Allow NSFW-tagged templates (default true)
>
> **caption\_style** `string ("tiktok" | "snapchat")`
>
> Style for single-caption renders (one caption on the image): "tiktok" (default, bold centered outlined text) or "snapchat" (translucent strip across the image). Both are drawn on top of the image. Multi-slot templates keep their own text boxes and ignore this.
>
> **include\_political** `boolean`
>
> Allow political-tagged templates (default true)
>
> **use\_search\_context** `boolean`
>
> Ground the joke in live web search results about the topic (default true). Disable for faster, purely template-driven output.

> [accordion] Generate video meme
>
> **Slug:** `MEMELORD_MCP_GENERATE_VIDEO_MEME`
>
> Generate AI-captioned video memes from a topic. Jester picks video templates (or uses template\_id), writes the caption text, and starts render jobs. Rendering is asynchronous: this returns job\_ids immediately — poll check\_video\_status (or list\_video\_jobs) until status is "completed" to get the MP4 URL. Billed against your usage balance.
>
> #### Input Parameters
>
> **count** `integer`
>
> Number of video memes (default 1, max 5)
>
> **prompt** `string` *required*
>
> Topic or idea for the video meme
>
> **category** `string ("trending" | "classic")`
>
> Restrict template selection to trending or classics
>
> **template\_id** `string`
>
> Pin a specific video template asset id (from search\_memes with type "video")
>
> **include\_nsfw** `boolean`
>
> Allow NSFW-tagged templates (default true)
>
> **include\_political** `boolean`
>
> Allow political-tagged templates (default true)
>
> **force\_caption\_style** `string ("top" | "tiktok")`
>
> Force the caption-bar path: "top" (letterbox above the clip) or "tiktok" (centered overlay). Omit to let templates with saved compositions use them.

> [accordion] Get account
>
> **Slug:** `MEMELORD_MCP_GET_ACCOUNT`
>
> Return the authenticated Memelord account: user id, display name, email, usage balance (USD, rounded to cents), whether billable tools can run, where to add credits, and how this MCP session is authenticated (OAuth or API key). Call this to confirm who you are acting as or to check whether billable tools will succeed. Free.

> [accordion] Get meme template
>
> **Slug:** `MEMELORD_MCP_GET_MEME_TEMPLATE`
>
> Fetch one template asset by id: name, type (meme | video | sticker), media URL, description, tags, dimensions, and how many text slots its layout has. Use it to inspect a search result before generating with template\_id. Free.
>
> #### Input Parameters
>
> **template\_id** `string` *required*
>
> Asset id from search\_memes or get\_trending\_memes

> [accordion] Get trending memes
>
> **Slug:** `MEMELORD_MCP_GET_TRENDING_MEMES`
>
> What's trending right now: the most recent curated trending templates with a short cultural-context blurb explaining the format. Use it to pick timely templates for generate\_caption\_meme / generate\_ai\_meme / generate\_video\_meme, or to answer "what memes are hot this week". NSFW drops are never included. Free.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Number of trending templates (default 3, max 12)
>
> **media\_type** `string ("image" | "video")`
>
> Only still images or only video clips. Omit for a mix.

> [accordion] List image tools
>
> **Slug:** `MEMELORD_MCP_LIST_IMAGE_TOOLS`
>
> Catalog of one-shot image tools you can run with run\_image\_tool: celebrity face swaps (Trump, Elon, Zuck, Vance, …), filters (Bust Down, Wojakify, GigaChad, Looksmaxxing, mugshot, Windows 95), and text-to-image generators (mascots, logos, Pokémon-style cards). Each entry lists its tool\_id, whether it needs an image and/or a prompt, and any extra params. Free.
>
> #### Input Parameters
>
> **category** `string ("image-to-image" | "image-text-to-image" | "text-to-image")`
>
> Filter by input contract

> [accordion] List video jobs
>
> **Slug:** `MEMELORD_MCP_LIST_VIDEO_JOBS`
>
> List your recent video jobs from every video tool, newest first, with status and MP4 URLs. Use it to recover job\_ids after a reconnect or to find finished videos without polling each job. Statuses are as last recorded; call check\_video\_status on an in-progress job to refresh it. Free.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Max jobs to return (default 10, max 50)
>
> **status** `string ("pending" | "processing" | "ready_to_process" | "rendering" | "completed" | "failed")`
>
> Only return jobs in this status

> [accordion] List video models
>
> **Slug:** `MEMELORD_MCP_LIST_VIDEO_MODELS`
>
> List the pro AI video models this account can run — Kling 3.0, Kling O3, Seedance, Wan 3.0, Cinema Studio 4.0 (run with run\_video\_model) — and Genjutsu character transpose (run with run\_genjutsu). Each entry lists required and optional inputs, rules, and params (options, ranges, defaults). Call this before run\_video\_model to pick a model and valid params. Free.

> [accordion] Run agent
>
> **Slug:** `MEMELORD_MCP_RUN_AGENT`
>
> Hand a natural-language request to Jester, Memelord's full meme agent — the same brain behind the Memelord chat. Jester decides what to do: search templates, caption a meme, remix a format, edit or generate an image, face-swap, make or caption a video, add text-to-speech or lipsync, convert to GIF, and more. Use this when a request does not map cleanly onto a specific tool ("turn this photo into a 3-panel meme about my cat", "make a video meme with the drake format about Mondays", "put my face on Elon"). Pass thread\_id from a previous result to continue the conversation. Returns the assistant's message plus any images; videos come back as job\_ids to poll with check\_video\_status. Billed against your usage balance.
>
> #### Input Parameters
>
> **count** `integer`
>
> How many results you want (default 1, max 5)
>
> **prompt** `string` *required*
>
> What you want, in plain language
>
> **thread\_id** `string`
>
> thread\_id from a previous run\_agent result to continue that conversation
>
> **image\_urls** `array`
>
> Public image URLs to work with (photos to meme-ify, faces to swap, images to edit); upload local files with upload\_media first

> [accordion] Run genjutsu
>
> **Slug:** `MEMELORD_MCP_RUN_GENJUTSU`
>
> Genjutsu character transpose: put a person or character into an existing video clip while keeping its motion, choreography, camera, timing, and audio ("put me in this music video", "swap the dancer for my character"). Needs the source clip (video\_url, or video\_job\_id of a finished video on this account) and 1-8 photos of who to put in (character\_image\_urls). Both must be real media the user provided — never invent, guess, or substitute URLs. When the user gives you local photos or a local clip, upload each with upload\_media first (clips over 3 MB via create\_media\_upload\_url) and pass the returned urls. If anything is missing the call returns status "needs\_input" listing everything still needed, with nothing started or charged: ask the user once, then call again. To generate new footage use run\_video\_model; for meme-template video clips use generate\_video\_meme. Returns a job\_id; poll check\_video\_status until completed. Billed against your usage balance per second of the source clip, only once the job starts.
>
> #### Input Parameters
>
> **mode** `string ("motion-transfer" | "object-swap")`
>
> motion-transfer (default, a person into the clip) or object-swap (swap an object / creature)
>
> **title** `string`
>
> Short title for the saved video
>
> **prompt** `string`
>
> Optional short direction in the user's words (wardrobe, lighting)
>
> **video\_url** `string`
>
> Public URL of the source clip (4-30 s; longer is trimmed); upload\_media returns one for a local file
>
> **resolution** `string ("720p" | "480p")`
>
> Output resolution (default 720p)
>
> **video\_job\_id** `string`
>
> job\_id of a finished video on this account, instead of video\_url
>
> **character\_image\_urls** `array`
>
> 1-8 public photo URLs of the person / character, clear front-facing first; upload local photos with upload\_media

> [accordion] Run image tool
>
> **Slug:** `MEMELORD_MCP_RUN_IMAGE_TOOL`
>
> Run one specific image tool from list\_image\_tools by tool\_id — e.g. "donald-trump-face-swapper" with a face photo, "bust-down-filter" on a portrait, or "mascot-generator" with a prompt. Provide image\_url for image-to-image tools, prompt for text-to-image tools, and params for any extra inputs the tool lists. Returns the resulting image URL(s). Prefer this over run\_agent when you already know exactly which tool you want. Billed against your usage balance.
>
> #### Input Parameters
>
> **params** `object`
>
> Extra tool-specific inputs keyed by the param key from list\_image\_tools
>
> **prompt** `string`
>
> Text input (required by text-to-image tools)
>
> **tool\_id** `string` *required*
>
> tool\_id from list\_image\_tools
>
> **image\_url** `string`
>
> Public URL of the input image (required by image tools); upload a local file with upload\_media first

> [accordion] Run video model
>
> **Slug:** `MEMELORD_MCP_RUN_VIDEO_MODEL`
>
> Generate new AI video footage with one model from list\_video\_models: from a prompt alone, a start frame (image\_url, optional end\_image\_url), or reference images / clips / audio. Use this for original footage ("a cinematic drone shot over Tokyo at night", "animate this photo"). For a meme template turned into a captioned video clip use generate\_video\_meme; for still images use run\_image\_tool or generate\_ai\_meme; to put a person into an existing clip use run\_genjutsu. Media must be public URLs the user provided — never invent or guess them; if the user gave you local files, upload them with upload\_media and pass the returned url. Invalid requests come back as status "invalid\_request" listing every problem, with nothing charged. Returns a job\_id; poll check\_video\_status until completed (usually a few minutes). Billed against your usage balance per generated second, only once the job starts.
>
> #### Input Parameters
>
> **seed** `integer`
>
> Seed for reproducibility (Wan only)
>
> **title** `string`
>
> Short title for the saved video
>
> **prompt** `string` *required*
>
> Scene, action, camera, lighting, and motion
>
> **variant** `string`
>
> Model version / quality tier from list\_video\_models
>
> **duration** `integer`
>
> Length in seconds, within the model's range
>
> **model\_id** `string ("kling" | "kling-o3" | "seedance" | "wan" | "cinema-studio")` *required*
>
> model\_id from list\_video\_models
>
> **image\_url** `string`
>
> Start / first-frame image (models with a start frame)
>
> **resolution** `string`
>
> One of the model's resolution options
>
> **aspect\_ratio** `string`
>
> One of the model's aspect\_ratio options
>
> **end\_image\_url** `string`
>
> Last-frame image; requires image\_url
>
> **generate\_audio** `boolean`
>
> Generate a soundtrack, where the model supports it
>
> **reference\_audio\_urls** `array`
>
> Reference audio (Audio 1, …)
>
> **reference\_image\_urls** `array`
>
> Reference images (Image 1, Image 2, … in the prompt)
>
> **reference\_video\_urls** `array`
>
> Reference clips for motion / camera (Video 1, …)

> [accordion] Search memes
>
> **Slug:** `MEMELORD_MCP_SEARCH_MEMES`
>
> Search Memelord's template library of memes, video clips, and stickers. Default method "semantic\_context" matches what a meme MEANS or depicts (natural-language queries like "when the deploy works on the first try"). Use "fulltext" for exact names and proper nouns ("drake", "spongebob"), "fuzzy" for misspellings, "semantic\_combined" when visual identity matters, or "semantic\_media" with media\_url to find templates that look like a given image. Results come best match first and include ids you can pass as template\_id to generate\_caption\_meme / generate\_ai\_meme / generate\_video\_meme / get\_meme\_template. Paging: each response has has\_more and next\_offset; to get the next page, repeat the exact same call (same query, method, filters, limit, min\_score) with offset set to next\_offset, and stop when has\_more is false (next\_offset is null). Pass ids you already have in exclude\_ids only when starting a fresh search, not while paging, or the pages shift. Free.
>
> #### Input Parameters
>
> **tags** `array`
>
> Only assets carrying any of these tags
>
> **type** `string ("meme" | "video" | "sticker")`
>
> Only return this asset type. Use "video" to find templates for generate\_video\_meme.
>
> **limit** `integer`
>
> Max results (default 20, max 100)
>
> **query** `string`
>
> Search text. Required unless method is "semantic\_media".
>
> **method** `string ("semantic_context" | "semantic_combined" | "semantic_media" | "fulltext" | "fuzzy")`
>
> semantic\_context (default) | semantic\_combined | semantic\_media | fulltext | fuzzy
>
> **offset** `integer`
>
> Results to skip (default 0, max 1000). Pass the previous response's next\_offset to fetch the next page.
>
> **media\_url** `string`
>
> Image/video URL to search by, for method "semantic\_media"
>
> **min\_score** `number`
>
> Override the per-method relevance floor (0-1). Lower it when a specific query returns nothing.
>
> **exclude\_ids** `array`
>
> Asset ids to skip (e.g. ones you already used)
>
> **include\_nsfw** `boolean`
>
> Include NSFW-tagged assets (default true)
>
> **face\_swappable** `boolean`
>
> Only templates with a face that can be swapped
>
> **template\_approved** `boolean`
>
> Only curator-approved templates

> [accordion] Upload media
>
> **Slug:** `MEMELORD_MCP_UPLOAD_MEDIA`
>
> Upload the user's own photo or video into their Memelord Uploads and get back an https url to pass to generate\_ai\_meme reference\_image\_urls, run\_image\_tool image\_url, run\_agent image\_urls, run\_genjutsu character\_image\_urls / video\_url, or run\_video\_model image and reference fields. Use it whenever the user gives you a local file or an attachment instead of a public link — never invent or guess media URLs. Send exactly one of: data\_base64 (file bytes, up to 3 MB decoded), source\_url (an https link to download), file (a host-provided file), or upload\_id (after PUTting a larger file to the upload\_url from create\_media\_upload\_url). Accepts image/jpeg, image/png, image/webp, video/mp4, video/quicktime, video/webm; images up to 10 MB, videos up to 100 MB. Genjutsu uses 4-30 s of a source clip (longer clips are trimmed to 30 s) and clear, front-facing photos work best for character\_image\_urls. The url is valid for 7 days; calling upload\_media again with the same upload\_id returns a fresh one. Free, and limited to 50 uploads per hour.
>
> #### Input Parameters
>
> **file** `object`
>
> A file the host attached (ChatGPT passes \{ download\_url, file\_id })
>
> **filename** `string`
>
> Original file name, shown in the user's Uploads
>
> **upload\_id** `string`
>
> upload\_id from create\_media\_upload\_url after you PUT the bytes, or from an earlier upload\_media result to get a fresh url
>
> **source\_url** `string`
>
> https URL to download the file from (a link the user shared)
>
> **data\_base64** `string`
>
> File bytes as base64 or a data: URL, up to 3 MB decoded. Larger files: create\_media\_upload\_url.
>
> **content\_type** `string`
>
> Optional MIME type (image/jpeg, image/png, image/webp, video/mp4, video/quicktime, video/webm); the file's bytes decide
