litellm-admin-mcp

litellm-admin-mcp

Exposes LiteLLM Proxy admin APIs as MCP tools for managing internal users, virtual keys, and spend logs via streamable-http, enabling agents to administer LiteLLM without custom HTTP glue.

Category
Visit Server

README

litellm-admin-mcp

LiteLLM Admin MCP server for OpenClaw. Exposes LiteLLM Proxy admin APIs (internal users, virtual keys, spend logs) as MCP tools over streamable-http, so agents can manage LiteLLM without custom HTTP glue.

将 LiteLLM Proxy 的管理能力封装为 MCP Server,供 OpenClaw Agent 通过 streamable-http 调用。

Overview

Item Detail
Transport MCP Streamable HTTP at /mcp
Backend LiteLLM Proxy REST API (LITELLM_BASE_URL)
Auth Authorization: Bearer sk-* pass-through per request (not env var)
Tools 11 admin tools (litellm_user_*, litellm_key_*, litellm_usage_*)
Health GET /health{"status":"ok"}
OpenClaw Agent ──streamable-http + Bearer sk-*──► litellm-admin-mcp :3100/mcp
                                                        │
                                                        ▼ Authorization pass-through
                                                  LiteLLM Proxy

Prerequisites

  • Node.js 20+ (engines.node in package.json)
  • A running LiteLLM Proxy with a valid admin key (sk-*)
  • For OpenClaw integration: OpenClaw CLI with MCP support

Install & Run

# Install dependencies
npm install

# Development (hot reload)
npm run dev

# Production build
npm run build
npm start

Default listen address: http://0.0.0.0:3100

  • Health: http://localhost:3100/health
  • MCP: http://localhost:3100/mcp

Docker Deployment

Quick start (docker compose)

docker compose up -d --build
docker compose logs -f litellm-admin-mcp
curl -s http://localhost:3100/health

Optional .env beside docker-compose.yml:

LITELLM_BASE_URL=http://192.168.91.200:8888
PORT=3100

Network note: The container must reach LiteLLM at LITELLM_BASE_URL. From inside Docker, 127.0.0.1 points to the container itself — use the host LAN IP or host.docker.internal (Docker Desktop).

Build and run manually

docker build -t litellm-admin-mcp:latest .

docker run -d \
  --name litellm-admin-mcp \
  -p 3100:3100 \
  -e LITELLM_BASE_URL=http://192.168.91.200:8888 \
  --restart unless-stopped \
  litellm-admin-mcp:latest

Stop: docker compose down or docker stop litellm-admin-mcp && docker rm litellm-admin-mcp

Environment Variables

Copy .env.example and adjust as needed:

cp .env.example .env
Variable Required Default Description
LITELLM_BASE_URL No http://192.168.91.200:8888 LiteLLM Proxy base URL (no trailing slash)
PORT No 3100 HTTP port for this MCP server
HOST No 0.0.0.0 Bind address

Example:

export LITELLM_BASE_URL=http://your-litellm-host:8888
export PORT=3100
export HOST=0.0.0.0
npm run dev

Admin key is not an environment variable. Configure it in the MCP client (e.g. OpenClaw headers), not in this server's env.

Authentication

Every request to /mcp must include:

Authorization: Bearer sk-<your-litellm-admin-key>

Behavior:

  1. Missing or invalid header (must start with Bearer sk-) → 401 from this server; LiteLLM is not called.
  2. Valid header → forwarded unchanged to LiteLLM API calls made by tool handlers.

OpenClaw (or any MCP client) supplies the key per session. Rotate keys in the client config without redeploying this server.

OpenClaw Configuration

Add to your OpenClaw MCP config (e.g. ~/.openclaw/config.json or project-level MCP settings):

{
  "mcp": {
    "servers": {
      "litellm-admin": {
        "url": "http://192.168.91.200:3100/mcp",
        "transport": "streamable-http",
        "headers": {
          "Authorization": "Bearer sk-your-admin-key"
        }
      }
    }
  }
}

Replace:

  • url — host/port where litellm-admin-mcp runs (path must be /mcp)
  • Authorization — your LiteLLM admin key (sk-*)

If OpenClaw and this server run on the same machine, http://127.0.0.1:3100/mcp works. For remote hosts, use the reachable IP/hostname and ensure firewall access to PORT.

MCP Tools (11)

Tool Description
litellm_user_list List LiteLLM internal users with optional filters and pagination
litellm_user_create Create a new LiteLLM internal user
litellm_user_update Update an existing LiteLLM internal user
litellm_user_delete Delete one or more LiteLLM internal users
litellm_user_info Get LiteLLM user details by user_id or user_email
litellm_key_list List LiteLLM virtual keys with optional filters and pagination
litellm_key_generate Generate a new LiteLLM virtual key
litellm_key_update Update an existing LiteLLM virtual key
litellm_key_delete Delete one or more LiteLLM virtual keys
litellm_key_info Get LiteLLM virtual key details by key hash or alias
litellm_usage_spend_logs Query LiteLLM spend logs with optional filters and pagination

Tool responses use a unified envelope:

{ "success": true, "data": {} }
{ "success": false, "error": { "status": 400, "message": "...", "detail": {} } }

Verification

Health check (no auth)

curl -s http://localhost:3100/health
# {"status":"ok"}

OpenClaw MCP probe

With the server running and OpenClaw configured:

openclaw mcp doctor --probe

Confirm litellm-admin (or your server alias) reports a healthy streamable-http connection and lists the 11 tools.

Testing

# Unit tests (default, no live LiteLLM)
npm test

# Optional integration tests against a real LiteLLM instance
RUN_INTEGRATION=1 npm test

# With custom LiteLLM URL / admin key for integration
LITELLM_BASE_URL=http://your-host:8888 LITELLM_ADMIN_KEY=sk-your-key RUN_INTEGRATION=1 npm test

Integration tests are read-only (user/list, key/list). They are skipped unless RUN_INTEGRATION=1.

Security

Treat the LiteLLM admin key (sk-*) as a root credential.

  • It can create/delete users and keys, change budgets, and read spend data.
  • Store it only in trusted MCP client config (OpenClaw headers), secret managers, or CI secrets — never commit it to git.
  • This server does not add a second auth layer; anyone who can reach /mcp with a valid admin key can perform admin actions on your LiteLLM Proxy.
  • Bind to 127.0.0.1 or place the service behind a private network / reverse proxy with TLS if exposed beyond localhost.
  • Do not log full sk-* values. key_generate may return a new plaintext key once (LiteLLM behavior); handle that response carefully.

Project Layout

Dockerfile            # Multi-stage production image
docker-compose.yml    # One-command deployment
src/
  server.ts           # Hono app, /health, /mcp transport
  litellm-client.ts   # LiteLLM HTTP client with auth pass-through
  tools/
    users.ts          # 5 user tools
    keys.ts           # 5 key tools
    usage.ts          # 1 usage tool
    index.ts          # MCP server registration
  utils/response.ts   # ok() / fail() helpers
tests/                # Vitest unit + optional integration tests

License

See repository license file if present.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured