Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

glif-mcp-server

MCP.Pizza Chef: glifxyz

glif-mcp-server is an MCP server enabling seamless execution of AI workflows from glif.app, including image generation, memes, and selfies. It supports all major multimedia AI models within a unified app environment. The server offers tools to run glifs, manage bots, and access detailed metadata about glifs, runs, and users. It also allows experimental customization of tools and agents, making it a versatile platform for integrating multimedia AI workflows into LLM-powered applications.

Use This MCP server To

Run multimedia AI workflows like image generation and memes Manage and customize AI bots and glif agents Access detailed metadata about AI runs and users Integrate glif.app AI tools into LLM environments Customize available AI tools dynamically via add/remove tool commands Execute complex AI workflows with multimedia inputs Use URI-based resources to fetch glif metadata Experiment with custom AI agent personalities and toolsets

README

glif-mcp-server

MCP server for running AI workflows from glif.app.

This server provides tools for running glifs, managing bots, and accessing glif metadata through the Model Context Protocol (MCP).

This server also allows for customizing all the tools available via add-tool, remove-tool etc meta-tools, including lot full glif agents as a set of tools (and personality). This is highly experimental.

For more info check out https://glif.app or join our Discord server: https://discord.gg/glif

Features

  • Run glifs with inputs
  • Get detailed information about glifs, runs, and users
  • Access glif metadata through URI-based resources

Setup

Running via npx (recommended)

If you have nodejs installed, you can run our @glifxyz/glif-mcp-server package via npx:

  1. Get your API token from https://glif.app/settings/api-tokens

  2. Add the server in your Claude Desktop config file. On macOS this is: ~/Library/Application Support/Claude/claude_desktop_config.json

    {
      "mcpServers": {
        "glif": {
          "command": "npx",
          "args": ["-y", "@glifxyz/glif-mcp-server@latest"],
          "env": {
            "GLIF_API_TOKEN": "your-token-here"
          }
        }
      }
    }

Running from a local checkout

First, checkout this code and install dependencies.

git clone https://github.com/glifxyz/glif-mcp-server
cd glif-mcp-server
npm install
npm run build
# there's now a build/index.js file which is what we'll run next

Then configure your MCP client (e.g. Claude Desktop) to load this server from disk.

{
  "mcpServers": {
    "glif": {
      "command": "node",
      "args": ["/path/to/glif-mcp/build/index.js"],
      "env": {
        "GLIF_API_TOKEN": "your-token-here"
      }
    }
  }
}

You can also specify glifs IDs (comma-separated) which will be loaded automatically when the server starts. This is useful for testing or if you want to share a pre-made glif configuration with someone else.

{
  "mcpServers": {
    "glif": {
      "command": "node",
      "args": ["/path/to/glif-mcp/build/index.js"],
      "env": {
        "GLIF_API_TOKEN": "your-token-here",
        "GLIF_IDS": "cm2v9aiga00008vfqdiximl2m,cm2v98jk6000r11afslqvooil,cm2v9rp66000bat9wr606qq6o",
        "IGNORE_SAVED_GLIFS": true,
      }
    }
  }
}

Run remotely with Smithery

To install glif-mcp for Claude Desktop automatically via Smithery, which hosts and runs the MCP server for you:

npx -y @smithery/cli install @glifxyz/glif-mcp-server --client claude

Usage Limits

Resources

  • glif://{id} - Get glif metadata
  • glifRun://{id} - Get run details
  • glifUser://{id} - Get user profile

Tools

General Glif Tools

  • run_glif - Run a glif with the specified ID and inputs
  • glif_info - Get detailed information about a glif including input fields
  • list_featured_glifs - Get a curated list of featured glifs
  • search_glifs - Search for glifs by name or description

Bot Tools

  • list_bots - Get a list of featured bots and sim templates
  • load_bot - Get detailed information about a specific bot, including its skills
  • save_bot_skills_as_tools - Save all skills from a bot as individual tools

User-specific Tools

  • my_glifs - Get a list of your glifs
  • my_glif_user_info - Get detailed information about your user account, recent glifs, and recent runs

Glif->Tool Tools (metatools)

  • save_glif_as_tool - Save a glif as a custom tool
  • remove_glif_tool - Remove a saved glif tool
  • remove_all_glif_tools - Remove all saved glif tools and return to a pristine state
  • list_saved_glif_tools - List all saved glif tools

How to turn glifs into custom tools

We have a general run_glif tool, but it (a) isn't very descriptive, and (b) requires doing a glif_info call first in order to learn how to call said glif. Plus, you need to know that glif exists.

We're experimenting with several new meta-tools which turn specific glifs into new standalone tools:

An example prompt session:

  • what are some cool new glifs?
  • [toolcall: list_featured_glifs...]
  • ok i like 1970s sci-fi book cover generator, make that into a tool called "scifi_book_image"
  • [toolcall: save_glif_as_tool glifId=... toolName=scifi_book_image]
  • [now user can just type "make sci fi book image of blah"]

You can list these special tools with list_saved_glif_tools and remove any you don't like with remove_glif_tool

Note that Claude Desktop requires a restart to load new tool definitions. Cline & Cursor seem to reload automatically on changes and requery for available tools

Info about authenticated user's glifs:

  • my_glifs - current user's published glifs (no drats)
  • my_liked_glifs - current user's liked glifs
  • my_runs - current user's public runs

MCP registries

smithery badge

Glif MCP server

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run dev

To run the test suite:

npm run test

And to continuously run tests on changes:

npm run test:watch

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

You can also look at the glif-mcp logs inside the Claude logs directy if you're using Claude Desktop.

Releasing a new version

  1. Edit package.json and src/index.ts and bump the version number
  2. Run npm install to update the versions stored in the lockfile
  3. Commit and push your changes to GitHub and merge to main
  4. If you have gh installed, switch to main and run npm run release which will create a git tag for the new version, push that tag to github, and use gh release create to publish a new version with an automatically-generated changelog. If you don't have gh, you can do the above manually in the GitHub web UI
  5. A GitHub Action will use the NPM_TOKEN secret to publish it to NPM

License

This project is licensed under the MIT License - see the LICENSE file for details.

glif-mcp-server FAQ

How do I get started with glif-mcp-server?
Obtain an API token from glif.app, then run the server via npx and configure your MCP host accordingly.
Can I customize the AI tools available in glif-mcp-server?
Yes, the server supports experimental features to add or remove tools and customize full glif agents as toolsets.
What types of AI workflows does glif-mcp-server support?
It supports multimedia AI workflows including image generation, memes, selfies, and other glif.app workflows.
How does glif-mcp-server integrate with LLMs?
It exposes glif workflows and metadata through MCP, allowing LLMs to run and manage AI tasks seamlessly.
Is glif-mcp-server limited to specific AI models?
No, it supports all major multimedia AI models integrated within glif.app.
Where can I find support or community help for glif-mcp-server?
You can join the glif Discord server at https://discord.gg/glif for community support.
What platforms can I run glif-mcp-server on?
It runs on any platform supporting Node.js and can be started easily via npx.
How do I access metadata about glifs and runs?
The server provides URI-based resources to fetch detailed metadata about glifs, runs, and users.