mcpField
M
memeport

memeport

Local
github.com/CloudCorpRecordsMedia & Design0Updated 1w ago

About memeport

memeport is an MCP server and CLI for searching meme templates and creating captioned memes through the Memeboat API. It supports per-caption styling and a layout that places captions in a bar above the image.

Key features

  1. 01Search meme templates by name or topic
  2. 02Inspect template dimensions and caption count
  3. 03Add styled captions to templates
  4. 04Return share-page and image URLs

Use cases

  1. 01Find a template for a topic
  2. 02Check a template before using it
  3. 03Create a meme with custom text styling

MCP support

Provides MCP tools to search templates, retrieve template details, and create captioned memes.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"cloudcorprecords-memeport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/memeport"
]
}
}
}
Run commandnpx -y @reneturcios/memeport

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@reneturcios/memeport0.1.0
ocighcr.io/cloudcorprecords/memeport:0.1.0

Tools

3

Saved tool list · updated 1w ago

ParameterTypeRequiredDescription
limitintegerNoMaximum templates to return
querystringYesName or topic to search for

Details

From the project README

memeport

Need a meme, not a design project? memeport searches a catalogue of more than 25,000 meme templates hosted by Memeboat, lets you inspect a template before you commit to it, and captions it for you — returning the finished meme's page URL and its direct image URL, ready to share.

Captions follow the template's own boxes. One caption lands at the bottom, two become top and bottom, and any more fill the template's caption boxes in order. Each caption can be a plain string, or an object that styles just that caption: its text, a color, an outline, and a font. A top-level font sets the default for every caption, and layout: "top" moves the captions into a white bar above the image instead of overlaying them on the picture.

Colours are a hex value (#rgb or #rrggbb) or one of white, black, red, yellow, blue, green. Fonts are impact, arial, helvetica, times, courier, titillium, thick, kalam, comic, notosans, and notosanshebrew.

Configuration

No account and no API key: the Memeboat API is free and anonymous.

export MEMEBOAT_API_URL="https://memebo.at"   # optional override

Leave MEMEBOAT_API_URL unset to use the public instance at https://memebo.at.

CLI

Each subcommand takes a single JSON argument string:

npx @reneturcios/memeport search_meme_templates '{"query":"drake","limit":5}'
npx @reneturcios/memeport get_meme_template '{"slug":"drake-hotline-bling"}'
npx @reneturcios/memeport create_meme '{"template":"drake-hotline-bling","texts":["no","yes"]}'
npx @reneturcios/memeport create_meme '{"template":"two-buttons","texts":[{"text":"one","color":"#fff","font":"impact"}],"font":"arial","layout":"top"}'
npx @reneturcios/memeport --version

Output is the upstream payload as JSON. Exit codes: 0 on success, 1 on a runtime error (including a validation error or a non-2xx upstream response), 2 on a usage error.

MCP server

npx -y @reneturcios/memeport mcp

MCP client config:

{
  "mcpServers": {
    "memeport": {
      "command": "npx",
      "args": ["-y", "@reneturcios/memeport", "mcp"]
    }
  }
}
Tools
  • search_meme_templates — Search meme templates by name or topic. Returns slugs, image URLs and a suggestedCaptionCount per template. Arguments: query (required), limit (optional).
  • get_meme_template — Get details for one meme template by slug: dimensions, image URL and caption count. Arguments: slug (required).
  • create_meme — Caption a meme template and get back the meme's page URL and direct image URL. Arguments: template and texts (required), font and layout (optional).

Docker

docker run -i ghcr.io/cloudcorprecords/memeport
docker run --rm ghcr.io/cloudcorprecords/memeport search_meme_templates '{"query":"cat"}'

Development

npm install
npm run build   # tsc -> dist/
npm test        # tsx --test test/*.test.ts (fake fetch, no network)
npm run dev     # run the CLI from source

License

MIT — Copyright (c) 2026 Rene Turcios

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.