modelcontextprotocol / modelcontextprotocol/inspector
docs/mcp-app-review.md is a manual review checklist with no automated CI enforcement
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 10.9k
- Forks
- 1.5k
- Avg merge
- 6h 17m
- Merged PRs (30d)
- 151
Description
Which version line?
v2 — current (@modelcontextprotocol/inspector@latest)
Which client?
All / shared core
Inspector version
2.7.0 (git tag) — static code-review finding, not run locally
Node version
N/A — static code review, no live run performed
Operating system (and browser, for the web client)
N/A — static code review
Transport
Not applicable / never connected
MCP server under inspection
N/A — this is a static code-review finding about docs/mcp-app-review.md, a review checklist, not a live reproduction against a running MCP server.
Steps to reproduce
Found via static review of the 2.7.0 tag source, not a live run.
- docs/mcp-app-review.md is a manual review checklist "for automated reviewers (CI, agents)" to run on-demand against an MCP app/server.
- A repo-wide search of scripts/ and .github/ finds no script or workflow that references "mcp-app-review" — unlike other conformance surfaces in the repo (e.g. verify-skills.mjs, dependabot-alerts.mjs, gate-lease checks), which ARE wired into CI/local:gate.
- So the checklist's guidance can silently drift out of sync with the code it describes, since nothing forces a contributor or CI run to apply it.
No live run was performed; this is based on reading the doc and searching the repo's scripts/CI config against the 2.7.0 tag.
Expected behavior
docs/mcp-app-review.md's checklist is either run automatically (a script/CI job that applies at least the mechanically-checkable items) the way other conformance docs in this repo are, or the doc explicitly says it is manual-only and by whom/how often it should be run.
Actual behavior
The doc is a well-written, on-demand checklist for reviewers (CI or agents) but nothing in scripts/ or .github/ actually invokes it — it's the only conformance surface in the repo without some automated enforcement, so it can go stale silently.
Suggested fix: turn at least the objectively-checkable items into a script (similar to verify-skills.mjs) runnable in CI/local:gate, or add a short note in the doc itself clarifying it's intentionally manual-only and stating who is expected to run it.
Logs, errors, or screenshots
No response
Already prototyped a fix?
No response
Before you submit
- I searched existing issues and this is not a duplicate.
- This is not a security vulnerability report (those go through the private advisory process).
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Read docs/mcp-app-review.md, then inspect scripts/ and .github/ for existing conformance checks such as verify-skills.mjs and local:gate wiring. Determine whether the mechanically checkable items can be enforced there, or whether the checklist should document its manual-only owner and schedule. Done means the checklist is either invoked by CI/local:gate or explicitly defines that manual process.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- github-actions, typescript
- Domain
- ci-cd, documentation
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 58/100