metamcp

MCP Aggregator, Orchestrator, Middleware, Gateway in one docker

Runssource: GitHubhomepageTypeScriptMITarchived upstreamcommit ff4ff2de9d25

TypeScript, MIT licensed. The project labels itself: mcp, mcp gateway, mcp host, mcp middleware, mcp server, mcp servers, mcp to openapi and mcp tools.

metamcp runs. An Argusic agent installed it in 8 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

pnpm install and build succeed, 187 backend tests pass, backend server starts on port 12009 with PostgreSQL bootstrap, health endpoint returns 200, MCP endpoint responds with valid JSON-RPC

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.18 (measured)
recorded runs
2
last tested
stars
2,761
forks
450
open issues
108
watchers
24
size
14 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing metamcp, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • PostgreSQL not available in container (no Docker, no system package manager)4 minutes
  • Workspace packages @repo/zod-types and @repo/trpc needed building before tests could resolve them2 minutes
Install time
8 minutes
Cold machine to finish
9 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
curl http://127.0.0.1:12009/health returned {"status":"ok"}, POST /metamcp/Public/mcp returned valid JSON-RPC, GET /metamcp/ returned endpoint listing, 187/187 tests passed
Model tokens used
98,213
Exact commit tested
ff4ff2de9d25
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

**Frontend:** Built successfully via Next.js with all pages compiled.
tokens used
98,213
Here's the comprehensive summary of everything I did and found:
**Install:** `pnpm install` succeeded with pnpm 10.29.3. `pnpm build` (via turborepo) built all pac…
**Tests:** `pnpm test` in `apps/backend` ran all 13 test suites — **187 tests passed, 0 failed**.
**PostgreSQL:** No Docker or system package manager was available. I downloaded a static PostgreSQL…
**Backend server:** Started on port 12009. All bootstrap operations completed (user, API keys, name…
- `GET /health` → `{"status":"ok"}`
- `GET /metamcp/` → lists the "Public" endpoint with MCP, SSE, and OpenAPI sub-paths
- `POST /metamcp/Public/mcp` → valid JSON-RPC response (`{"jsonrpc":"2.0","error":{"code":-32000,"m…
**Frontend:** Built successfully via Next.js with all pages compiled.

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Recovered from all 2 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 8 minutes to install, slower than the median of the 15 comparable projects Argusic has measured.

Of the 16 mcp projects Argusic has installed and timed, metamcp was the 13th fastest to reach a running state, and 14 of 16 reached one at all.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 8 minutes after the clone.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.18
Argusic Runner1/3Runs100.000.02

Topics (from GitHub)

mcpmcp-gatewaymcp-hostmcp-middlewaremcp-servermcp-serversmcp-to-openapimcp-toolsmodel-context-protocolmodel-context-protocol-servermodel-context-protocol-serversopen-webuiopenapiself-hostedvibe-coding

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/metamcp.svg)](https://argusic.com/subject/metamcp)

Questions

Does metamcp run?
Yes. metamcp runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test metamcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit ff4ff2de9d25. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test metamcp?
The run that produced this verdict cost $0.18: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does metamcp take to install?
8 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does metamcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing metamcp?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does metamcp compare with the alternatives?
Of the 16 mcp projects Argusic has installed and timed, metamcp was the 13th fastest to reach a running state, and 14 of 16 reached one at all.
Where is the evidence for metamcp?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion