by glifxyz
Run AI workflows on Glif.app via MCP — ComfyUI image generators, meme & selfie creators, chained LLM calls and more for
Connects to Glif.app to run AI workflows like image generators, meme creators, and chained LLM processes directly from your MCP client.
Glif is an official MCP server published by glifxyz that provides AI assistants with tools and capabilities via the Model Context Protocol. Run AI workflows on Glif.app via MCP — ComfyUI image generators, meme & selfie creators, chained LLM calls and more for It is categorized under ai ml, developer tools.
You can install Glif in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Glif is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
I recommend Glif for teams standardizing on MCP; the explainx.ai page compares cleanly with sibling servers.
We evaluated Glif against two servers with overlapping tools; this profile had the clearer scope statement.
Glif is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Glif has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Glif is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
According to our notes, Glif benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Glif has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
Glif is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
Glif reduced integration guesswork — categories and install configs on the listing matched the upstream repo.
Strong directory entry: Glif surfaces stars and publisher context so we could sanity-check maintenance before adopting.
showing 1-10 of 32
MCP server for running AI workflows from glif.app.
For more info check out https://glif.app or join our Discord server: https://discord.gg/glif
If you have nodejs installed, you can run our @glifxyz/glif-mcp-server package via npx:
Get your API token from https://glif.app/settings/api-tokens
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"
}
}
}
}
git clone https://github.com/glifxyz/glif-mcp-server
cd glif-mcp-server
npm install
npm run build
Then configure your MCP client:
{
"mcpServers": {
"glif": {
"command": "node",
"args": ["/path/to/glif-mcp/build/index.js"],
"env": {
"GLIF_API_TOKEN": "your-token-here"
}
}
}
}
You can also specify workflow IDs (comma-separated) which will be loaded automatically:
{
"mcpServers": {
"glif": {
"command": "node",
"args": ["/path/to/glif-mcp/build/index.js"],
"env": {
"GLIF_API_TOKEN": "your-token-here",
"GLIF_IDS": "cm2v9aiga00008vfqdiximl2m,cm2v98jk6000r11afslqvooil"
}
}
}
}
Environment variables:
GLIF_API_TOKEN - Required. Your API token from https://glif.app/settings/api-tokensGLIF_IDS - Optional. Comma-separated workflow IDs to load as tools automaticallyIGNORE_DISCOVERY_TOOLS - Set to true to disable discovery toolsAGENT_TOOLS - Set to true to enable agent toolsrun_workflow - Run a workflow with the specified ID and inputsworkflow_info - Get detailed information about a workflowlist_featured_workflows - Get a curated list of featured workflowssearch_workflows - Search for workflows by name or descriptionmy_workflows - Get a list of your workflowsmy_user_info - Get detailed information about your accountAGENT_TOOLS=true)list_agents - Get a list of agents with optional filteringload_agent - Load an agent and get its details including personality and workflowsglif://{id} - Get workflow metadataglifRun://{id} - Get run detailsglifUser://{id} - Get user profilenpm install
npm run build
npm run dev # auto-rebuild
npm run test # run tests
npm run inspector
package.json and src/index.ts and bump the versionnpm install to update lockfilenpm run release (requires gh CLI)MIT - see LICENSE
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.