What is Mcp Server Llmling

mcp-server-llmling is a server designed for the Machine Chat Protocol (MCP) that utilizes the LLMling backend to provide a YAML-based configuration system for LLM applications.

Use cases

Use cases include creating custom LLM applications, managing content dynamically, integrating with development environments, and extending LLM capabilities through tools and prompts.

How to use

To use mcp-server-llmling, configure it in your environment by defining a YAML configuration that specifies resources, prompts, and tools. You can integrate it with editors like Zed by adding it as a context server in the settings.

Key features

Key features include resource management for various content types, a tool system for executing Python functions, prompt management with static and dynamic prompts, and multiple transport options for communication.

Where to use

undefined

mcp-server-llmling

Read the documentation!

LLMling Server Manual

Overview

mcp-server-llmling is a server for the Machine Chat Protocol (MCP) that provides a YAML-based configuration system for LLM applications.

LLMLing, the backend, provides a YAML-based configuration system for LLM applications.
It allows to set up custom MCP servers serving content defined in YAML files.

• Static Declaration: Define your LLM’s environment in YAML - no code required
• MCP Protocol: Built on the Machine Chat Protocol (MCP) for standardized LLM interaction
• Component Types:
  • Resources: Content providers (files, text, CLI output, etc.)
  • Prompts: Message templates with arguments
  • Tools: Python functions callable by the LLM

The YAML configuration creates a complete environment that provides the LLM with:

• Access to content via resources
• Structured prompts for consistent interaction
• Tools for extending capabilities

Key Features

1. Resource Management

• Load and manage different types of resources:
  • Text files (PathResource)
  • Raw text content (TextResource)
  • CLI command output (CLIResource)
  • Python source code (SourceResource)
  • Python callable results (CallableResource)
  • Images (ImageResource)
• Support for resource watching/hot-reload
• Resource processing pipelines
• URI-based resource access

2. Tool System

• Register and execute Python functions as LLM tools
• Support for OpenAPI-based tools
• Entry point-based tool discovery
• Tool validation and parameter checking
• Structured tool responses

3. Prompt Management

• Static prompts with template support
• Dynamic prompts from Python functions
• File-based prompts
• Prompt argument validation
• Completion suggestions for prompt arguments

4. Multiple Transport Options

• Stdio-based communication (default)
• Server-Sent Events (SSE) / Streamable HTTP for web clients
• Support for custom transport implementations

Usage

With Zed Editor

Add LLMLing as a context server in your settings.json:

{
  "context_servers": {
    "llmling": {
      "command": {
        "env": {},
        "label": "llmling",
        "path": "uvx",
        "args": [
          "mcp-server-llmling",
          "start",
          "path/to/your/config.yml"
        ]
      },
      "settings": {}
    }
  }
}

With Claude Desktop

Configure LLMLing in your claude_desktop_config.json:

{
  "mcpServers": {
    "llmling": {
      "command": "uvx",
      "args": [
        "mcp-server-llmling",
        "start",
        "path/to/your/config.yml"
      ],
      "env": {}
    }
  }
}

Manual Server Start

Start the server directly from command line:

# Latest version
uvx mcp-server-llmling@latest

1. Programmatic usage

from llmling import RuntimeConfig
from mcp_server_llmling import LLMLingServer

async def main() -> None:
    async with RuntimeConfig.open(config) as runtime:
        server = LLMLingServer(runtime, enable_injection=True)
        await server.start()

asyncio.run(main())

2. Using Custom Transport

from llmling import RuntimeConfig
from mcp_server_llmling import LLMLingServer

async def main() -> None:
    async with RuntimeConfig.open(config) as runtime:
        server = LLMLingServer(
            config,
            transport="sse",
            transport_options={
                "host": "localhost",
                "port": 3001,
                "cors_origins": ["http://localhost:3000"]
            }
        )
        await server.start()

asyncio.run(main())

3. Resource Configuration

resources:
  python_code:
    type: path
    path: "./src/**/*.py"
    watch:
      enabled: true
      patterns:
        - "*.py"
        - "!**/__pycache__/**"

  api_docs:
    type: text
    content: |
      API Documentation
      ================
      ...

4. Tool Configuration

tools:
  analyze_code:
    import_path: "mymodule.tools.analyze_code"
    description: "Analyze Python code structure"

toolsets:
  api:
    type: openapi
    spec: "https://api.example.com/openapi.json"

[!TIP]
For OpenAPI schemas, you can install Redocly CLI to bundle and resolve OpenAPI specifications before using them with LLMLing. This helps ensure your schema references are properly resolved and the specification is correctly formatted. If redocly is installed, it will be used automatically.

Server Configuration

The server is configured through a YAML file with the following sections:

global_settings:
  timeout: 30
  max_retries: 3
  log_level: "INFO"
  requirements: []
  pip_index_url: null
  extra_paths: []

resources:
  # Resource definitions...

tools:
  # Tool definitions...

toolsets:
  # Toolset definitions...

prompts:
  # Prompt definitions...

MCP Protocol

The server implements the MCP protocol which supports:

1. Resource Operations

   • List available resources
   • Read resource content
   • Watch for resource changes

2. Tool Operations

   • List available tools
   • Execute tools with parameters
   • Get tool schemas

3. Prompt Operations

   • List available prompts
   • Get formatted prompts
   • Get completions for prompt arguments

4. Notifications

   • Resource changes
   • Tool/prompt list updates
   • Progress updates
   • Log messages