mcp-debugging
Skill4 starsChanged 20 days agoMITView on GitHub
Diagnose MCP connector failures by separating stored connection state from live upstream tool evidence.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- a11y-auditorSkill
- api-contract-reviewSkill
- backend-releaseSkill
- bug-diagnosisSkill
- client-copy-reviewSkill
- codebase-designSkill
- code-reviewSkill
- create-issueSkill
- create-prSkill
- create-taskSkill
- dependency-upgradeSkill
- deploy-evidenceSkill
- design-expertSkill
- design-system-docsSkill
- design-system-setupSkill
- domain-modelingSkill
- e2e-verifySkill
- evidence-auditSkill
- feature-discoverySkill
- frontend-releaseSkill
- generate-readmeSkill
- handoffSkill
- implement-taskSkill
- incident-responseSkill
- init-projectSkill
- live-docsSkill
- memory-curatorSkill
- plan-expertSkill
- planning-featuresSkill
- project-memory-initSkill
- project-memory-refreshSkill
- project-profileSkill
- project-releaseSkill
- proof-runnerSkill
- release-checklistSkill
- researchSkill
- security-hardeningSkill
- security-reviewSkill
- tddSkill
- wiki-forgeSkill
- wiki-initSkill
- wiki-querySkill
- wiki-syncSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Use when an MCP connector, tool, token, or upstream integration appears connected but behavior fails.
- Distinctive: line 16
Prefer a live tool call or minimal endpoint check that exercises the failing capability.
- Distinctive: line 18
Never expose secrets, tokens, cookies, or auth headers.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 Debugging
Use when an MCP connector, tool, token, or upstream integration appears connected but behavior fails.
Principles
- Stored connection state is not proof that the upstream service accepts the token/session.
- Prefer a live tool call or minimal endpoint check that exercises the failing capability.
- Capture exact error codes, tool names, timestamps, and sanitized payloads.
- Never expose secrets, tokens, cookies, or auth headers.
Output
## MCP Debug Report
**Connector:** <name>
**Claimed state:** <configured/active/unknown>
**Live check:** <command/tool and result>
**Root cause:** <best-supported cause or unknown>
**User action needed:** <reconnect, grant permission, rotate token, none>
**Evidence:** <sanitized snippets>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.