fastapi_mcp
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
Runssource: GitHubhomepagePythonMITcommit e5cad13cabfc
Python, MIT licensed. The project labels itself: ai, authentication, authorization, claude, cursor, fastapi, llm and mcp.
fastapi_mcp runs. An Argusic agent installed it in 2 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The fastapi-mcp package installs, its full test suite (89 tests) passes, and the MCP StreamableHTTP endpoint responds with a valid initialize handshake (HTTP 200, protocol version 2024-11-05, server capabilities).
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
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.
- Installed mcp 2.2.0 (latest) but the project's lock file pins mcp 1.12.1 and the tests use the v1 API1 minute
- Dev extras not installed by pip (pytest etc missing)0.3 minutes
- Pip install failed due to externally-managed-environment (PEP 668)0.2 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 5 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- `pytest tests/ -v` exited 0, 89 passed, 83% coverage; plus `curl equivalent via httpx POST /mcp` returned HTTP 200 with valid MCP initialize response
- Model tokens used
- 144,317
- Exact commit tested
- e5cad13cabfc
- 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.
}
},
"serverInfo": {
"name": "FastAPI",
"version": "1.30.0"
}
}
}
The MCP server responded to a real initialize request with HTTP 200 and proper capabilities. All ve…
tokens used
144,317
The MCP server responded to a real initialize request with HTTP 200 and proper capabilities. All ve…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.
- Installed in 2 minutes, faster than the median of the 48 comparable projects Argusic has measured.
- Recovered from all 3 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.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 49 ai projects Argusic has installed and timed, fastapi_mcp was the 8th fastest to reach a running state, and 38 of 49 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 2 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
Topics (from GitHub)
aiauthenticationauthorizationclaudecursorfastapillmmcpmcp-servermcp-serversmodelcontextprotocolopenapiwindsurf
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/fastapi-mcp)Questions
- Does fastapi_mcp run?
- Yes. fastapi_mcp runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test fastapi_mcp?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit e5cad13cabfc. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test fastapi_mcp?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does fastapi_mcp take to install?
- 2 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 fastapi_mcp need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing fastapi_mcp?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does fastapi_mcp compare with the alternatives?
- Of the 49 ai projects Argusic has installed and timed, fastapi_mcp was the 8th fastest to reach a running state, and 38 of 49 reached one at all.
- Where is the evidence for fastapi_mcp?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.