Litellm MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 108 installs a week from pypi.
Give AI agents access to 100+ LLMs. Call any model, compare outputs.
The linked repository no longer exists on GitHub — it was deleted or made private.
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add litellm-mcp -- uvx litellm-mcp
{
"mcpServers": {
"litellm-mcp": {
"args": [
"litellm-mcp"
],
"command": "uvx"
}
}
}
[mcp_servers.litellm-mcp]
command = "uvx"
args = ["litellm-mcp"]
{
"mcpServers": {
"litellm-mcp": {
"args": [
"litellm-mcp"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"litellm-mcp": {
"args": [
"litellm-mcp"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
OPENAI_API_KEY (OpenAI API key for GPT models), ANTHROPIC_API_KEY (Anthropic API key for Claude models).
The author declared them in the registry entry; get the values from the project itself.
Governed app access for AI agents: 1,000+ apps & 12,000+ tools via Code Mode MCP.
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
Give AI agents access to Gmail, Calendar, Drive, and more — multi-account, manifest-driven
Create and run any AI agents systems from 6k+ tools. Give your AI hands access to your Android.
Read-only access to Epivo's live course catalogue for AI agents.
Give AI agents secure access to ZERNO project briefs, tasks, and context over remote MCP.
Pay-per-call ($0.01 USDC) model-routing for AI coding agents: which LLM to call, cost vs. quality.
AI inference pricing for agents: live and historical model prices, provider comparison.
Answers built from our own checks of this server.