Litellm Mcp

io.github.shin-bot-litellmPublished by GitHub account shin-bot-litellmv1.0.1Updated Oct 24, 2026

Give AI agents access to 100+ LLMs. Call any model, compare outputs.

VerifiedSTDIODesktop onlyAI & ML

Overview

AI-generated overview

Local MCP server that gives an AI assistant access to 100+ LLMs through LiteLLM, so it can call models and compare their outputs.

What you can do
  • Call a wide range of LLM providers and models through one LiteLLM-backed interface.
  • Compare outputs from different models side by side.
  • Reach Claude models and GPT models using the corresponding provider API keys.
When to use it
Useful when you want an assistant to query several model providers from one place, or to compare answers across models without wiring up each provider separately.
Requirements
Runs as a local process over stdio, installed from the PyPI package litellm-mcp and started with Python. Needs an ANTHROPIC_API_KEY for Claude models and an OPENAI_API_KEY for GPT models. Desktop only; no web execution.
Before you install
Requires provider API keys (ANTHROPIC_API_KEY, OPENAI_API_KEY) that are passed as environment variables. Model calls are billed by the respective providers, so usage can cost money. Prompts and content sent to models leave your machine and go to those third-party providers.

Installation

In SourceWeft

  1. Open Litellm Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.