LLMling MCP Server

LLMling

A framework for declarative LLM application development focused on resource management, prompt templates, and tool execution.

This package provides the backend for two consumers: A MCP server and a pydantic-AI based Agent

Core Concepts

LLMLing provides a YAML-based configuration system for LLM applications. It allows to set up custom MPC 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

• Written from ground up in modern python (minimum 3.12 required)

• 100% typed

• pydantic(-ai) based

An overview about the whole system:

graph TB
    subgraph LLMling[LLMling Core Package]
        RT[RuntimeConfig]

        subgraph Core_Components[Core Components]
            Resources[Resource Management- Load files/URLs- Process content- Watch changes]
            Tools[Tool System- Execute functions- Register new tools- OpenAPI integration]
            Prompts[Prompt System- Static/Dynamic prompts- Template rendering- Completion support]
        end

        CLI[Core CLI- config add/remove/list- resource list/load- tool list/execute- prompt list/render]

        Core_Components -->|YAML configuration| RT
        RT -->|All components| CLI
        CLI -->|modify| Core_Components
    end

    subgraph Direct_Access[mcp-server-llmlingDirect Component Access]
        MCP[HTTP/SSE Server- Start/Stop server]
        MCP_CLI[Server CLI- Start/Stop server]
        Injection[Injection Server- Inject componentsduring runtime]
    end

    subgraph Function_Access[llmling-agentAccess via Function Calling]
        LLM[LLM Integration- Function calling- Resource access- Tool execution- Structured output]
        Agent_CLI[Agent CL