Base
Hardened build
minimal ports, security patches applied at build time
MetaMCP MCP Aggregator on Ubuntu 24.04 LTS
Azure
Artificial Intelligence (AI)
MetaMCP, the open source model context protocol aggregator: group many MCP servers behind one namespaced, authenticated endpoint, with middleware and a management UI, secured from first boot by cloudimg.
Overview
MetaMCP is an open source aggregator, orchestrator, middleware and gateway for the Model Context Protocol, the standard that lets AI assistants and agents call external tools. It groups many separate MCP servers into namespaces and exposes each namespace as one endpoint, reachable over the streamable HTTP and SSE transports and as an OpenAPI REST surface, so a client connects once and reaches every underlying tool. A management web interface registers the downstream servers, composes them into namespaces, applies per namespace tool middleware such as filtering, and issues API keys that gate access to the aggregated endpoints, giving teams a single controlled front door to their MCP tool estate instead of wiring every assistant to every server by hand.
It suits platform and AI engineering teams who are running more than one MCP server and want central registration, namespacing, middleware and authenticated access over the tools their agents can call, hosted inside their own cloud account.
Why the cloudimg image
cloudimg ships MetaMCP secure by default with no surviving default login. On the first boot of every instance a unique administrator password, the session authentication secret, the database password and an API key are all generated fresh and the administrator credential is written to a root only file, so no two deployments share a secret and the upstream defaults never govern a running instance. Public sign up is disabled once the single administrator is seeded, the database is bound to a private network rather than exposed, the application is fronted by a TLS reverse proxy, and unauthenticated requests to the aggregated endpoints are refused. Because an aggregator is only useful once something is aggregated, the appliance registers one real reference MCP server and a namespace and endpoint at first boot, and the build verifies a real tool call travelling through the aggregated endpoint end to end, plus a full create and read back of a server, namespace and endpoint through the management API. The base is fully patched with unattended security upgrades enabled, and every deployment is paired with a step by step guide and backed by 24/7 cloudimg support.
Common uses
- One authenticated endpoint aggregating many MCP servers
- Namespacing and tool middleware for AI tool servers
- A management UI and API keys for MCP access control
See it running
Real screenshots taken while testing this image against its deployment guide.
More in Artificial Intelligence (AI)
Ie
Infinity Embeddings Server
Artificial Intelligence (AI)
This image runs Infinity 0.0.77, the high-throughput, low-latency server for text embedding and reranking models (michae...
Ls
Label Studio
Artificial Intelligence (AI)
This image runs Label Studio 1.23, the open source data labeling and annotation platform for machine learning - label te...
LibreChat AI Chat Platform - with
Artificial Intelligence (AI)
This image runs LibreChat, the open source AI chat platform - a self-hosted, ChatGPT-style web interface that connects t...
Lo
LiteLLM
Artificial Intelligence (AI)
This image runs LiteLLM 1.88, the open source gateway that puts a single OpenAI-compatible API in front of more than 100...
Lo
LocalAI
Artificial Intelligence (AI)
This image runs LocalAI, the free, open source, self hosted alternative to the OpenAI API.
MLflow
Artificial Intelligence (AI)
This image runs MLflow 3.13, the open source platform for the machine learning lifecycle - experiment tracking, a model ...