cross-llm

A Model Context Protocol (MCP) server that provides access to multiple Large Language Model (LLM) APIs including ChatGPT, Claude, Gemini, Mistral, Kimi K2, and DeepSeek.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio jamesanz-cross-llm-mcp node /absolute/path/to/cross-llm-mcp/build/index.js \
  --env XAI_API_KEY="your_grok_api_key_here" \
  --env KIMI_API_KEY="your_kimi_api_key_here" \
  --env GEMINI_API_KEY="your_gemini_api_key_here" \
  --env OPENAI_API_KEY="your_openai_api_key_here" \
  --env MISTRAL_API_KEY="your_mistral_api_key_here" \
  --env DEEPSEEK_API_KEY="your_deepseek_api_key_here" \
  --env ANTHROPIC_API_KEY="your_anthropic_api_key_here" \
  --env PERPLEXITY_API_KEY="your_perplexity_api_key_here"

How to use

Cross-LLM MCP Server provides unified access to multiple large language model providers from a single API surface. It exposes tools to call individual providers (e.g., call-chatgpt, call-claude, call-deepseek, call-gemini, call-grok, call-kimi, call-perplexity, call-mistral) as well as combined tools (call-all-llms, call-llm) for parallel or selective querying. Users can set tag-based preferences to optimize model selection for coding, business, reasoning, math, creative, or general tasks, and they can log prompts to analyze history and statistics. To use it, deploy the MCP server via Node.js, then interact with the exposed tools by sending JSON payloads that specify the tool and its arguments, such as a prompt, temperature, or max_tokens. The server can be integrated with editors or environments like Cursor or Claude Desktop, enabling seamless multi-provider AI workflows.

How to install

Prerequisites:

Node.js v18+ and npm

Installation steps:

Clone the repository or install from npm:
- From source: git clone https://github.com/JamesANZ/cross-llm-mcp.git cd cross-llm-mcp npm install npm run build
- Or install globally via npm (if published): npm install -g cross-llm-mcp
Build (if installing from source): npm run build

3)Run the server: node build/index.js

4)Configure API keys (environment variables) before running in production. Example keys to set:

OPENAI_API_KEY
ANTHROPIC_API_KEY
DEEPSEEK_API_KEY
GEMINI_API_KEY
XAI_API_KEY
KIMI_API_KEY
PERPLEXITY_API_KEY
MISTRAL_API_KEY

Note: If you are integrating with Claude Desktop, you may configure the mcpServers entry as shown in the Claude Desktop integration guide.

Additional notes

Tips and considerations:

Environment variables are required for each provider you intend to use. Only set keys for providers you have access to.
For production deployments, consider setting a dedicated process manager (e.g., PM2) and securely managing environment variables.
When using Cursor or Claude Desktop, you can point tools at the built index.js path and use the provided key placeholders to configure API access.
Regularly monitor prompt history and model usage to optimize costs and model selection strategies.
Ensure Node.js version compatibility with the MCP SDK and build outputs.
If you encounter connectivity issues, verify that API keys are valid and not restricted by IP or usage quotas.

Related MCP Servers

lobehub

72.8k

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

chatgpt-on-wechat

41.7k

CowAgent是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、拥有长期记忆并不断成长。同时支持飞书、钉钉、企业微信应用、微信公众号、网页等接入，可选择OpenAI/Claude/Gemini/DeepSeek/ Qwen/GLM/Kimi/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助手和企业数字员工。

repomix

22.2k

📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, DeepSeek, Perplexity, Gemini, Gemma, Llama, Grok, and more.

ai-guide

8.5k

程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享大模型选择指南（DeepSeek / GPT / Gemini / Claude）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（RAG / MCP / A2A）、AI 编程教程、AI 工具用法（Cursor / Claude Code / OpenClaw / TRAE / Lovable / Agent Skills）、AI 开发框架教程（Spring AI / LangChain）、AI 产品变现指南，帮你快速掌握 AI 技术，走在时代前沿。本项目为开源文档版本，已升级为鱼皮 AI 导航网站

deep-research

4.5k

Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.

archestra

3.6k

Secure cloud-native MCP registry, gateway & orchestrator