
Master MCP Server
Aggregates multiple MCP servers behind a single, secure endpoint with unified tool/resource discovery, OAuth authentication, and resilient request routing. Enables users to manage and interact with multiple MCP backends through one centralized interface with load balancing and circuit breakers.
README
Master MCP Server
Master MCP Server aggregates multiple MCP servers behind a single, secure endpoint. It provides configuration-driven module loading, unified capability discovery, request routing with resilience, and first-class OAuth flows for multi-backend authentication.
Highlights
- Aggregates multiple MCP servers with tool/resource discovery and namespacing
- OAuth support: master token pass-through, delegated provider flows, proxy refresh
- Config-driven setup with JSON/YAML, schema validation, and secret resolution
- Resilient routing: load-balancing, retries with backoff/jitter, circuit-breakers
- Cross-platform: Node.js server and Cloudflare Workers runtime
- Production-ready deployment: Docker, Cloudflare Workers, Koyeb
- Testing strategy and CI-ready structure
Quick Start (Node.js)
- Install dependencies (requires network):
npm ci
- Configure environment (copy and edit):
cp .env.example .env
- Run in dev mode:
npm run dev
- Health and Metrics:
GET /health
→{ ok: true }
GET /metrics
→ basic system metrics
- MCP endpoints (HTTP gateway):
POST /mcp/tools/list
POST /mcp/tools/call
with{ name, arguments }
POST /mcp/resources/list
POST /mcp/resources/read
with{ uri }
See docs/
for full guides and end-to-end examples.
Documentation
- Docs index:
docs/index.md
- Getting started:
docs/getting-started/overview.md
- Guides:
docs/guides/*
- API reference: generated into
docs/api/reference/
(see below) - Configuration reference:
docs/configuration/*
- Deployment:
docs/deployment/*
- Troubleshooting:
docs/troubleshooting/*
- Contributing:
docs/contributing/*
Generate API Docs
We use TypeDoc (Markdown) to generate API docs from TypeScript.
- Install (requires network):
npm i -D typedoc typedoc-plugin-markdown
- Generate docs:
npm run docs:api
Outputs to docs/api/
.
Examples
Working examples live in examples/
:
- Basic Node:
examples/basic-node
- Cloudflare Worker:
examples/cloudflare-worker
- Advanced Routing:
examples/advanced-routing
- OAuth Delegation:
examples/oauth-delegation
- Testing Patterns: see
/tests
anddocs/examples/testing.md
Each example has a README with run instructions.
Deployment
- Docker:
deploy/docker/*
and top-levelDockerfile
/docker-compose.yml
- Cloudflare Workers:
deploy/cloudflare/*
withwrangler.toml
- Koyeb:
deploy/koyeb/koyeb.yaml
- CI/CD examples: see
docs/deployment/cicd.md
Architecture
Contributing & Support
- See
docs/contributing/*
for development workflow and guidelines - See
docs/troubleshooting/index.md
for solutions - Open an issue or discussion for help and ideas
License
See LICENSE
. This repository currently uses UNLICENSED for private/internal use.
Recommended Servers
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.
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.
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.

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

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.