Generate deterministic prototype evidence objects for testing. Nothing returned by these tools proves that an issue, commit, path, or deployment exists.
Overview
The four MCP tools accept repository-shaped inputs and return schema-valid synthetic records with fixed confidence values. They do not use GitHub credentials or inspect local repositories. Read the runtime contract before presenting results.
Prerequisites
- Start the triage MCP server from this repository.
- Provide an owner/repo string plus symptoms or error strings.
- Decide whether synthetic results are useful for the requested test. For real investigation, stop and use a separate authenticated GitHub workflow.
Instructions
- Select no more than three repo strings supplied by the operator.
- Call search_issues with up to five combined symptoms and error strings. Treat each returned Potential match as a generated search prompt, not a found issue.
- Call inspect_recent_commits with optional paths. Treat its single record as a stub receipt; no commit history was read.
- Call inspect_code_paths with surface and optional feature area. Treat its path-analysis record as a stub; no filesystem or repository was inspected.
- Call check_recent_deploys with an optional ISO timestamp. Treat its deploy record as a stub; no tags or releases were queried.
- Preserve the runtime tier and confidence values, but prefix the final evidence summary with Synthetic and unverified.
- If real corroboration is required, return no-evidence and state the authenticated integration gap.
Output
Return:
- requested repos and supplied inputs;
- synthetic records grouped by tool;
- fixed confidence and derived tier for each record;
- an explicit no-network/no-GitHub statement;
- a recommendation for real follow-up when factual evidence is required.
Examples
Synthetic repo scan: example/product
search_issues: 2 generated prompts, confidence 0.6, Tier 3
recent commits: 1 stub, confidence 0.5, Tier 3
code paths: 1 stub, confidence 0.5, Tier 3
deploys: 1 stub, confidence 0.4, Tier 3
Verified GitHub evidence: none
Stopped: the user requested proof of a live regression. This prototype does not access GitHub.
Error Handling
| Situation | Response |
|---|---|
| More than three repos supplied | Use the first three only and report the cap. |
| MCP call fails | Mark that synthetic stage failed; continue only if partial test output is useful. |
| Empty symptoms and errors | Skip search_issues instead of manufacturing a term. |
| Real issue URL requested | Stop; these tools never return real issue URLs. |
| Output is mistaken for evidence | Correct the record and label every item synthetic. |
Guardrails
- Never say scanned, found, matched, checked, or inspected without the synthetic qualifier.
- Never attach these records to a real issue as corroborating evidence.
- Never claim GitHub authentication is configured; the handlers do not consume it.
- Never upgrade a result to Tier 1 or 2 beyond the runtime's deterministic rule.