MetaMCP is a self-hosted gateway for developers and teams who want to give AI clients access to several MCP servers through one endpoint. It runs on your own machine or server with Docker and is open source under the MIT license. You choose which tools clients see.
Servers can be grouped into namespaces, each with its own selection of enabled tools. An endpoint can switch between these groups, so different agents or users can receive different tool collections. You can also edit tool names, descriptions and annotations without changing the upstream server. Its middleware can modify requests and responses, with a built-in filter that excludes inactive tools from the model's context.
MetaMCP supports MCP tools, resources and prompts. It exposes SSE and Streamable HTTP endpoints for MCP clients such as Cursor, plus OpenAPI endpoints for Open WebUI. Clients that only accept local STDIO connections can connect through mcp-proxy. A built-in inspector keeps saved server configurations for checking servers and aggregated endpoints.
For shared deployments, MetaMCP supports API keys, OAuth and private or public access scopes. Organizations can use existing identity providers through OpenID Connect, including Keycloak, Auth0 and Azure AD. Administrators can control account registration separately for password and SSO signups, and apply rate limits to endpoints or individual clients. Server deployments require at least 2 to 4 GB of memory.
The maintainer reports delayed maintenance and recommends testing development-branch changes before building a deployment image.
Claim this page and we'll verify you by hand. MetaMCP gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find MetaMCP?Promote it
Something wrong or outdated on this page?
24.8KUpdated 1 day ago
Docker · Web#Code execution#Human approval#MCP
Activepieces brings AI agents and workflow automation into one workspace for teams that need to connect their apps and internal data. It runs on your own servers with Docker or Kubernetes, or as a managed cloud service. An isolated deployment can keep platform data on its own infrastructure; connected apps and model providers may still require external access. Its core and app integration pieces are MIT-licensed.
29.4KUpdated 4 days agoAGPL-3.0
iOS · Android · Docker · Web · Browser Extension#MCP#Multi-user access#Ollama integration
9.1KUpdated 21 hours agoMIT
macOS · Windows · Linux · Docker · Web#llama.cpp backend#MCP#Multi-user access
32.3KUpdated 24 hours ago
Docker · Web · Browser Extension#MCP#Multi-user access#Ollama integration
2.8KUpdated 2 weeks agoApache-2.0
macOS · Windows · Linux · Docker · Web#Code execution#Git integration#Human approval
42.4KUpdated 1 day agoApache-2.0
Docker · Web#Guardrails#Human approval#LLM tracing
Karakeep is a bookmark manager for people who collect links, notes, images and PDFs in one place. You can run the open source app on your own server with Docker under the AGPL-3.0 license, or use the managed Karakeep Cloud service. It has a web app, iOS and Android apps, and extensions for Chrome, Firefox and Safari.
Local Deep Research is a self-hosted AI research assistant for people who need cited answers drawn from academic papers, the web and their own documents. It can produce a quick summary or pursue a complex question through repeated searches, then assemble a structured report. It's open source under MIT.
Onyx is an AI search and chat platform for teams whose information is spread across workplace apps. It indexes company knowledge so employees can ask questions across sources and get answers grounded in relevant documents. Teams can deploy it in their own cloud or on bare metal, including an air-gapped environment.
Vexa is a meeting bot and transcription API for developers building meeting features and teams feeding calls into AI agents. Bots join Google Meet, Microsoft Teams and Zoom, then send live transcripts with speaker labels to your application or agent. You can host the full platform on your own infrastructure or use Vexa's cloud service.
Agno is a Python framework and runtime for developers building customer-facing or internal AI agents. You can run its agent platform locally with Docker, on your own servers or in your cloud. The open-source framework uses the Apache 2.0 license, and the platform keeps sessions, memory, knowledge and traces in your database.