MCP LLM

What is MCP LLM?

MCP LLM is an MCP server that provides access to LLMs using the LlamaIndexTS library. It offers tools for code generation, documentation, and question answering, intended for developers who want to integrate LLM capabilities into AI‑powered coding workflows.

How to use MCP LLM?

Install via Smithery with npx -y @smithery/cli install @sammcj/mcp-llm --client claude, or manually from source by cloning the repository, running npm install and npm run build, then updating your MCP client configuration. Use the provided tools (generate_code, generate_code_to_file, generate_documentation, ask_question) by sending JSON‑formatted requests.

Key features of MCP LLM

• Generate code from a natural‑language description.
• Write generated code directly to a file at a specific line.
• Generate documentation for existing code.
• Ask open‑ended questions to the LLM.
• Supports both relative and absolute file paths.

Use cases of MCP LLM

• Rapidly scaffold functions or algorithms from a description.
• Insert generated code into an existing file at a precise location.
• Automatically produce JSDoc or similar docs for a code snippet.
• Get answers to programming questions with optional contextual hints.

FAQ from MCP LLM

What tools does MCP LLM provide?

It provides four tools: generate_code, generate_code_to_file, generate_documentation, and ask_question.

How do I install MCP LLM?

You can install it automatically via Smithery using the command npx -y @smithery/cli install @sammcj/mcp-llm --client claude, or manually by cloning the repository and running npm install and npm run build.

Can I generate code directly into a file?

Yes, the generate_code_to_file tool accepts a filePath, lineNumber, and replaceLines parameter to write generated code to a specific file and line.

Does the server support relative file paths in generate_code_to_file?

Yes. If a relative path is provided, it is resolved relative to the current working directory of the MCP server.

Which LLM library does MCP LLM use?

It uses the LlamaIndexTS library under the hood.