mcp-compat-check
Skill7 starsChanged 21 days agoMITView on GitHub
Checks in about a minute whether an MCP server's metadata survives the clients it will run in (Claude Code, claude.ai, Cowork, ChatGPT Chat and Work, Codex): reads tools/list and the server instructions over HTTP or stdio, and scores each tool against each client's measured limits on descriptions, server instructions, input schemas and output schemas. Invoke when asked to check, health-check, lint or score an MCP server, to ask "will this server work in ChatGPT / Codex / claude.ai", "why does the agent ignore my description or parameter docs", or to compare public servers. Hands fixes to the rich-domain-mcp-server skill.
In this repository5 other files it gives its agents.
- mcp-compat-checkSkill
- rich-domain-mcp-serverSkill
- run-evalSkill
- rich-domain-mcp-serverSkill
- run-evalSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Never put a token in the command yourself: ask the user to export it as an environment variable, and pass the variable.
- Very specific: line 74
Start with the "Start here" list.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
mcp-compat-check — does the metadata reach the model on every client?
A server can ship perfect metadata and still not deliver it, because each client cuts or drops
different surfaces. This check compares what a server ships with what each client delivered when
it was measured (2026-09-27; evidence: rich-domain-mcp-server → references/evidence.md, tag
HD). It is static: no model and no tool calls, so it runs in seconds and gives the same answer
every time.
Run it
node .claude/skills/mcp-compat-check/check.mjs https://example.com/mcp
node .claude/skills/mcp-compat-check/check.mjs --header "Authorization: Bearer $TOKEN" https://example.com/mcp
node .claude/skills/mcp-compat-check/check.mjs --stdio -- node dist/stdio.js
node .claude/skills/mcp-compat-check/check.mjs --json https://example.com/mcp # for CI or diffing
node .claude/skills/mcp-compat-check/check.mjs --oauth https://mcp.example.com/mcp # OAuth servers (needs @modelcontextprotocol/sdk)Never put a token in the command yourself: ask the user to export it as an environment variable,
and pass the variable. For OAuth servers use --oauth: it opens the user's browser, the user signs
in and approves, and the token lives only in the checking process. Run one OAuth server at a time,
and tell the user which service the next tab is for.
What it checks, per client column
| surface | Claude only (Code, claude.ai, Cowork) | ChatGPT / Codex only | all clients |
| tool description | ≤ 4,096 (Claude Code 2.1.296+ for a tool sent up front, and Cowork; 2,048 before 2.1.296) | no cut measured | ≤ 4,096 |
| server instructions | ≤ 4,096, and nothing required (claude.ai chat gets none) | ≤ 512, and nothing required (Work gets none) | ≤ 512, nothing required |
| input schema | whole | ≤ 5,000 serialized, or every describe is dropped (bisected on Codex; ChatGPT Work consistent, not bisected) | ≤ 5,000 |
| output schema | never delivered: meaning there is review-only | delivered on Codex and Work | review-only |
It also flags: guidance that lives mostly in the server instructions, tools with a first sentence
too short to be found by clients that load tools by search, missing annotations, and the size of
tools/list, which is re-sent every turn.
Reading the report
The Verdict table has one column per client group and one row per surface:
| row | what it counts |
| overall | the worst surface in that column, which surfaces fail, and how many tools are affected |
| tool description | tools whose description is longer than the column's cut |
| server instructions | their length against the column's budget, and whether the guidance lives there; within budget is green, with a note that some clients deliver none |
| input schema | tools whose serialized schema is over 5,000, so Codex and ChatGPT Work drop every describe |
| output schema | tools that ship one; on the Claude clients it never arrives, so meaning found only there is flagged |
- 🟢 portable: within every measured limit for that column.
- 🟡 host-dependent: it arrives on some clients, or is never needed; review it. Output-schema meaning is fine if the same meaning travels in the field names or the response, which a static check cannot see.
- 🔴 not portable: the server relies on a surface or size that some measured client in that column does not deliver.
A portability finding, not a quality rating. A protocol-correct, well-built server can be red: the protocol lets it ship metadata that some clients never pass on. The report's last section lists the rule behind every cell, so anyone can recompute the matrix.
Start with the "Start here" list. For each fix, use the rich-domain-mcp-server skill: its
Budgets by target client table has the rule and its evidence, and its REQUIRED guidance-tool
pattern holds detail that does not fit a budget.
Limits
- One day's client versions. Re-measure before relying on a number: the quote probe and the Codex
request trace are in
rich-domain-mcp-server→references/delivery.md. - It does not call tools, so it cannot see the response, where most meaning should live.
- A green report means the metadata arrives. It says nothing about whether the metadata is right.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

