High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
MCP server for calling other LLMs from agents
MCP LLM is an MCP server that gives your agent access to other LLMs. It provides tools for generating code, writing code directly into a file, generating documentation, and asking questions.
Builders who use MCP-capable agents and want them to offload code and documentation tasks to another LLM.
You can have your agent call a separate LLM to draft code, fill files, and write docs without leaving your workflow.
What it does
Generate code
Takes a description and language, then returns generated code.
Write code to a file
Generates code and writes it to a specific file and line number, with optional line replacement.
Generate documentation
Produces documentation from source code in a chosen format such as JSDoc.
Ask a question
Sends a question and optional context to the LLM for an answer.
MCP setup options
Supports installation through Smithery and manual setup from source for MCP clients.
How to get it
- 1To install LLM Server for Claude Desktop automatically via Smithery
npx -y @smithery/cli install @sammcj/mcp-llm --client claude
- 2Install dependencies
npm install
- 3Build the project
npm run build
- 4The repository includes an example script that demonstrates how to use the MCP server…
node examples/use-mcp-server.js
README
MCP LLM
An MCP server that provides access to LLMs using the LlamaIndexTS library.

Features
This MCP server provides the following tools:
generate_code: Generate code based on a descriptiongenerate_code_to_file: Generate code and write it directly to a file at a specific line numbergenerate_documentation: Generate documentation for codeask_question: Ask a question to the LLM

Installation
Installing via Smithery
To install LLM Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @sammcj/mcp-llm --client claude
Manual Install From Source
- Clone the repository
- Install dependencies:
npm install
- Build the project:
npm run build
- Update your MCP configuration
Using the Example Script
The repository includes an example script that demonstrates how to use the MCP server programmatically:
node examples/use-mcp-server.js
This script starts the MCP server and sends requests to it using curl commands.
Examples
Generate Code
{
"description": "Create a function that calculates the factorial of a number",
"language": "JavaScript"
}
Generate Code to File
{
"description": "Create a function that calculates the factorial of a number",
"language": "JavaScript",
"filePath": "/path/to/factorial.js",
"lineNumber": 10,
"replaceLines": 0
}
The generate_code_to_file tool supports both relative and absolute file paths. If a relative path is provided, it will be resolved relative to the current working directory of the MCP server.
Generate Documentation
{
"code": "function factorial(n) {\n if (n <= 1) return 1;\n return n * factorial(n - 1);\n}",
"language": "JavaScript",
"format": "JSDoc"
}
Ask Question
{
"question": "What is the difference between var, let, and const in JavaScript?",
"context": "I'm a beginner learning JavaScript and confused about variable declarations."
}
License
Files in the repo
- .github
- examples
- src
- .gitignore
- .nvmrc
- CHANGELOG.md
- Dockerfile
- legit.png
- LICENSE
- package-lock.json
- package.json
- README.md
- sample-mcp-settings.json
- screenshot1.png
- screenshot2.png
- smithery.yaml
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。