PluginBench
MCP Server

LiteLLM Multi-Model API MCP Server

io.github.BerriAI/litellm-mcp

RepositoryRegistry
How to choose

What this kind of tool is for

  • Hand your agent a structured way to call a model or an inference API.
  • Compare outputs from two different providers on the same prompt.
  • Wire retrieval, embeddings, or generation into an existing agent workflow.

How to compare servers like this

Provider coverage:
Match the tool's supported providers and models to the ones your project uses.
Cost exposure:
Model-backed tools spend real API budget; check how usage and limits are configured.
Maintenance signal:
The provider landscape shifts weekly; prefer tools updated within the last few months.
Config surface:
Prefer tools whose environment-variable or config keys are documented plainly.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the LiteLLM Multi-Model API MCP server?

Access 100+ LLMs with one API: GPT-4, Claude, Gemini, Mistral, and more.

How to install LiteLLM Multi-Model API

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • OPENAI_API_KEY
    secret

    OpenAI API key for GPT models

  • ANTHROPIC_API_KEY
    secret

    Anthropic API key for Claude models

  • LITELLM_API_BASE

    LiteLLM Proxy base URL (optional)

  • LITELLM_API_KEY
    secret

    LiteLLM Proxy API key (optional)

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "litellm-mcp": {
      "command": "python",
      "args": [
        "litellm-mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
        "ANTHROPIC_API_KEY": "<YOUR_ANTHROPIC_API_KEY>",
        "LITELLM_API_BASE": "<YOUR_LITELLM_API_BASE>",
        "LITELLM_API_KEY": "<YOUR_LITELLM_API_KEY>"
      }
    }
  }
}

Related MCP servers

Find patent infringers with 9 AI models. Search products & standards from your AI client.

Evidence-bound second-opinion audit of an agent conclusion against caller-supplied evidence.

SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.

View repository →

MCP server for Quantinuum Nexus, wrapping the qnexus SDK. Not affiliated with Quantinuum.

1
Python
Apache-2.0
View repository →

Local index and search of your AI coding-agent threads across 11 tools, with semantic search, knowledge distillation, and MCP integration.

15
Rust
AGPL-3.0
View repository →

AI-assisted Valkey/Redis observability for Claude Code and other MCP clients.

1.2k
TypeScript
View repository →