Job 04 · Not yet tested
Which MCP server should I plug into my agent?
Official MCP servers, installed in Claude Desktop and Cursor, then checked with five scripted calls whose results are known first.
Agent builders picking a server to install, not a framework to write.
The standard test
Pack 0.1.0 · specified · Install and five calls
Install in Claude Desktop and Cursor, 5 scripted calls
Setup
Install the server in Claude Desktop and in Cursor using the vendor's documented config. Then run the same five calls in each client. Calls hit a fixture account or a local stub, never a customer's production data. Expected outputs are written before the run.
Inputs
The install docs, fixture credentials, and the five-call script.
Time limit
One wall-clock cap for every tool in the job. The number is published with the pack before the first run and does not move between tools.
What we record
- Install worked per client
- Calls passed
- Human fixes
- Time
- Tool version
How the FitScore is built
FitScore = weighted average × 20, rounded to the nearest integer. The weighted average is the sum of (criterion score × weight) divided by 100.
- Output quality30
- Reliability15
- Cost and free tier15
- Speed10
- Setup friction10
- Agent, API, and MCP support10
- Privacy and data10
5 excellent · 4 good · 3 usable · 2 poor · 1 fails. Full method.
Candidates
Candidates for MCP servers. This order is the launch list, not a ranking. No FitScores are published.
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Version and plan recorded when a test is published
Questions this page answers
- Which MCP server should I plug into my agent?
- FitForTool has not published a FitScore for this job. The launch candidates are GitHub MCP Server, Playwright MCP, Context7, Supabase MCP, Notion MCP, Stripe MCP, and Sentry MCP. Each one is listed as not yet tested. A ranking is published only after every tool in the comparison has had the same test pack run, and a person has reviewed the result. Until that page shows a FitScore, there is no winner.
- How will FitForTool test mcp servers?
- Install in Claude Desktop and Cursor, 5 scripted calls. Install the server in Claude Desktop and in Cursor using the vendor's documented config. Then run the same five calls in each client. Calls hit a fixture account or a local stub, never a customer's production data. Expected outputs are written before the run. We record install worked per client, calls passed, human fixes, time, and tool version. Those notes are then scored from 1 to 5 on seven shared criteria. The pack has been specified and has not been run.
- Can a vendor pay to rank higher on this job?
- No. FitForTool does not sell position or score. A sponsorship, if we run one later, is labelled and sits outside the ranked list. An affiliate link is disclosed and does not change order. A vendor may ask for a retest, and we rerun the same pack. Sponsors do not see the result before it is public.
- What does "Not yet tested" mean?
- The tool is a candidate for this job. There is no published hands-on run, so there is no FitScore, no criterion score, and no rank. Research-only is a different label, used when we have read the docs and still have not run the pack. Neither label is a score.