JamesANZ/cross-llm-mcp
by Various
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.
MCP
JamesANZ/cross-llm-mcp
Added 1 June 2026
Overview
A Model Context Protocol (MCP) server that provides a unified interface to multiple LLM APIs including ChatGPT, Claude, Gemini, Mistral, Kimi K2, and DeepSeek. It allows developers to switch between models or route requests through a single MCP endpoint without changing client code.
Best for
Best for
Developers who need a unified MCP-based gateway to multiple LLM APIs
Use cases
- Unifying access to multiple LLM providers behind one MCP endpoint
- Seamlessly switching between different models during development or testing
- Building applications that can leverage diverse AI capabilities through a standardized protocol
How to use
Install
npm install -g cross-llm-mcp Tools exposed
call-chatgptcall-claudecall-deepseekcall-geminicall-grokcall-kimicall-perplexitycall-mistralcall-huggingfacecall-all-llmscall-llmget-user-preferencesset-user-preferencesget-models-by-tagget-prompt-historyget-prompt-statsdelete-prompt-entriesclear-prompt-history
Tested with
Cursor, Claude Desktop
Example client config
[object Object] Notes
A Model Context Protocol (MCP) server that provides a unified interface to multiple LLM APIs including ChatGPT, Claude, Gemini, Mistral, Kimi K2, and DeepSeek. It allows developers to switch between models or route requests through a single MCP endpoint without changing client code.
15 stars on GitHub. Last updated 2026-04-17. Licensed MIT.
Use cases
- Unifying access to multiple LLM providers behind one MCP endpoint
- Seamlessly switching between different models during development or testing
- Building applications that can leverage diverse AI capabilities through a standardized protocol
Pros
- Supports a broad range of major LLM providers
- Standardized MCP interface simplifies integration
- Open source with a clear TypeScript codebase for customization
Cons
- Low community adoption (15 stars) may indicate limited support and documentation
- Requires managing multiple API keys and provider configurations
- MCP protocol is less commonly used than direct API calls, adding potential complexity
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Supports a broad range of major LLM providers
- Standardized MCP interface simplifies integration
- Open source with a clear TypeScript codebase for customization
Cons
- Low community adoption (15 stars) may indicate limited support and documentation
- Requires managing multiple API keys and provider configurations
- MCP protocol is less commonly used than direct API calls, adding potential complexity
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
LiteLLM 🚅
Community
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, Vertex
vLLM
Community
A high-throughput and memory-efficient inference and serving engine for LLMs
ollama
Community
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.