LiteLLM Multi-Model API
Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.
Open the source (opens github.com) https://github.com/berriai/litellm-agent-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: ANTHROPIC_API_KEY, LITELLM_API_KEY, OPENAI_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.BerriAI.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
litellm-mcp@1.0.2
From the server's entry in the official MCP Registry
Settings it asks for
OPENAI_API_KEYsecret · OpenAI API key for GPT modelsANTHROPIC_API_KEYsecret · Anthropic API key for Claude modelsLITELLM_API_BASE· LiteLLM Proxy base URL (optional)LITELLM_API_KEYsecret · LiteLLM Proxy API key (optional)
Related
-
1flowbase
MCP serversBuild for agents — from the AI Gateway to the entire application stack.
git clone https://github.com/taichuy/1flowbase.git -
litellm-mcp
MCP serversGive AI agents access to 100+ LLMs. Call any model, compare outputs.
litellm-mcp@1.0.1 -
9routerx
MCP servers9RouterX (9R Next Go Generation): Single-binary Go AI router, LLM gateway & 20-40% token saver. Route Claude Code, Cursor & Codex across 155 providers, 28 OAuth & 248 free models (24 keyless) — OpenAI, Claude, Gemini, DeepSeek, Groq, Ollama & MCP.
git clone https://github.com/yanstd888/9routerx.git -
ai-tutorial
MCP servers中文 AI 应用实战教程(含英文版):AgentScope Java、MCP、RAGFlow、FastGPT、Langfuse、LiteLLM、CopilotKit,本机实测,在线阅读与源码同仓。Hands-on Chinese AI tutorials (English edition available) covering AgentScope Java, MCP, RAGFlow, FastGPT, Langfuse, LiteLLM, and CopilotKit.
git clone https://github.com/ybak/ai-tutorial.git -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
openmake_llm
MCP serversOpen-source, self-hosted AI workspace for local and open-weight LLMs with vLLM, LiteLLM, autonomous agents, MCP tools, deep research, artifacts, and BYOK.
git clone https://github.com/openmake/openmake_llm.git