MCP-Bridge

A middleware to provide an openAI compatible endpoint that can call MCP tools

Runs with mockssource: GitHubPythonMITcommit df1dcc58cac7

Python, MIT licensed. The project labels itself: ai, claude, mcp, mcp server, mcp servers, model context protocol, openai and openai api.

MCP-Bridge runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1.5 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

uv sync installed all 70 dependencies and built the project, the server starts and responds to health (200), MCP tools/prompts/resources (200 each), docs (200), and SSE endpoint (200). The /v1/models endpoint returns 500 because no inference server is configured.

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 86 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
86 / 100
cost of the verifying run
$0.11 (measured)
recorded runs
2
last tested
stars
922
forks
117
open issues
37
watchers
8
size
1 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.

What went wrong, in the agent's own words

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

  • pydantic field name 'json' shadows parent attribute in InitialSettings
Install time
2 minutes
Cold machine to finish
6 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
curl -s http://127.0.0.1:8000/health returned 200 with body {"status":"ok","unhealthy_events":[]}; GET /mcp/tools returned 200 {}; GET /mcp/prompts returned 200 {}; GET /mcp/resources returned 200 {}; GET /docs returned 200; GET /mcp-server/sse/ returned 200
Model tokens used
723,613
Exact commit tested
df1dcc58cac7
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

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

exec
/bin/sh -lc 'ps aux | grep -E "mcp_bridge|uvicorn" | grep -v grep | head -5' in /work/repo
 succeeded in 0ms:
runner       903  0.0  0.0 205540 30404 ?        Ssl  01:21   0:00 uv run python -m mcp_bridge.main
runner       907  2.6  0.0 216112 133144 ?       Sl   01:21   0:00 /work/repo/.venv/bin/python -m m…
All endpoints are functioning correctly. Let me clean up the server and finalize.
exec
/bin/sh -lc "ps aux | grep -E \"mcp_bridge|uvicorn\" | grep -v grep | awk '{print "'$2}'"' | xargs …
 succeeded in 0ms:
server stopped
tokens used
723,613

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

  • Installed in 1.5 minutes, faster than the median of the 236 comparable projects Argusic has measured.
  • Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
  • 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

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.

Of the 237 ai projects Argusic has installed and timed, MCP-Bridge was the 47th fastest to reach a running state, and 168 of 237 reached one at all.

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 Runner2/3Unverified80.000.04
Argusic Runner1/3Runs with mocks92.000.11

Topics (from GitHub)

aiclaudemcpmcp-servermcp-serversmodel-context-protocolopenaiopenai-api

Embed the badge

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

[![Tested by Argusic](https://argusic.com/badge/MCP-Bridge.svg)](https://argusic.com/subject/mcp-bridge)

Questions

Does MCP-Bridge run?
MCP-Bridge runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test MCP-Bridge?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit df1dcc58cac7. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test MCP-Bridge?
The run that produced this verdict cost $0.11: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does MCP-Bridge take to install?
1.5 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 MCP-Bridge need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing MCP-Bridge?
1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does MCP-Bridge compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, MCP-Bridge was the 47th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for MCP-Bridge?
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