LiteLLM Multi-Model API
Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
litellm-mcpclaude mcp add litellm-multi-model-api -e 'OPENAI_API_KEY=<your openai_api_key>' -e 'ANTHROPIC_API_KEY=<your anthropic_api_key>' -e 'LITELLM_API_BASE=<LITELLM_API_BASE>' -e 'LITELLM_API_KEY=<your litellm_api_key>' -- python litellm-mcp==1.0.2
{
"mcpServers": {
"litellm-multi-model-api": {
"command": "python",
"args": [
"litellm-mcp==1.0.2"
],
"env": {
"OPENAI_API_KEY": "<your openai_api_key>",
"ANTHROPIC_API_KEY": "<your anthropic_api_key>",
"LITELLM_API_BASE": "<LITELLM_API_BASE>",
"LITELLM_API_KEY": "<your litellm_api_key>"
}
}
}
}
Environment variables
OPENAI_API_KEYsecret OpenAI API key for GPT modelsANTHROPIC_API_KEYsecret Anthropic API key for Claude modelsLITELLM_API_BASELiteLLM Proxy base URL (optional)LITELLM_API_KEYsecret LiteLLM Proxy API key (optional)
Frequently asked questions
What is LiteLLM Multi-Model API?
Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.
How do I install LiteLLM Multi-Model API?
It runs on your machine. In Claude Code: claude mcp add litellm-multi-model-api -e 'OPENAI_API_KEY=<your openai_api_key>' -e 'ANTHROPIC_API_KEY=<your anthropic_api_key>' -e 'LITELLM_API_BASE=<LITELLM_API_BASE>' -e 'LITELLM_API_KEY=<your litellm_api_key>' -- python litellm-mcp==1.0.2. For other clients, paste the JSON configuration from this page into their MCP settings.
Does LiteLLM Multi-Model API need an API key?
Yes. It expects OPENAI_API_KEY, ANTHROPIC_API_KEY, LITELLM_API_KEY, which you set in its configuration.
Is LiteLLM Multi-Model API open source?
Its code is public on GitHub, but the repository does not declare a standard license.
Who maintains LiteLLM Multi-Model API?
It is published by BerriAI. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.