LLMling

Easy MCP (Model Context Protocol) servers and AI agents, defined as YAML.

Catalog onlyCatalog onlySTDIO

Overview

LLMling is a framework for declarative LLM (Large Language Model) application development, focusing on resource management, prompt templates, and tool execution, defined using YAML.

To use LLMling, you can create a YAML configuration file to define your LLM's environment, set up custom MCP (Model Context Protocol) servers, and utilize the command-line interface (CLI) for various operations.

YAML-based configuration for easy setup of LLM applications. - Support for static declaration of resources, prompts, and tools. - Integration with MCP for standardized LLM interaction. - CLI commands for managing resources, executing tools, and rendering prompts.

Developing LLM applications with custom resource management.
Automating tasks using LLMs through defined prompts and tools.
Creating interactive agents that utilize LLM capabilities for various applications.

Add to your AI client

Use these steps to connect LLMling in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "llmling-phil65": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-llmling-phil65"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "llmling-phil65": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-llmling-phil65"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "llmling-phil65": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-llmling-phil65"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "llmling-phil65": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-llmling-phil65"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "llmling-phil65": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-llmling-phil65"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "llmling-phil65": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-llmling-phil65"
      ]
    }
  }
}

FAQ

Can LLMling be used for any LLM?

Yes! LLMling is designed to work with any LLM that can interact through the MCP protocol.

Is LLMling open-source?

Yes! LLMling is available on GitHub and is open for contributions.

What programming language is required?

LLMling is written in Python and requires Python 3.12 or higher.

Developer tools