feat(mcp): expose .loopover.yml config recommendations as a read-only MCP tool

[oktofeesh1]

Summary

• Add a new read-only MCP tool loopover_get_config_recommendation to src/mcp/server.ts, wrapping the existing buildGittensorConfigRecommendationResponse (src/api/routes.ts) exactly like the sibling loopover_get_registration_readiness/loopover_get_label_audit tools, so MCP clients can fetch .loopover.yml recommendations without direct REST access.
• Register the new tool in the repo-owner-intake MCP client profile's recommendedTools list (packages/loopover-mcp/bin/loopover-mcp.js), since that profile's stated purpose already names config recommendations but had no tool for it.
• Closes feat(mcp): expose .loopover.yml config recommendations as a read-only MCP tool (loopover_get_config_recommendation) #5823

Scope

• The PR title follows type(scope): short summary Conventional Commit format, for example fix(api): restore profile access checks.
• This PR is focused and does not mix unrelated backend, UI, MCP, docs, dependency, and deploy changes.
• This follows CONTRIBUTING.md and does not reintroduce GitHub Pages, VitePress, site/, or CNAME.
• I linked a currently open issue this PR resolves (e.g. Closes #123) — a linked open issue is required for every contributor PR.

Validation

• git diff --check
• npm run actionlint
• npm run typecheck
• npm run test:coverage locally; codecov/patch requires ≥99% coverage of the lines AND branches you changed (aim for 100% on your diff so CI variance does not fail near the threshold). Global coverage is a non-blocking trend with a loose 90% backstop, not the gate.
• npm run test:workers
• npm run build:mcp
• npm run test:mcp-pack
• npm run ui:openapi:check
• npm run ui:lint
• npm run ui:typecheck
• npm run ui:build
• npm audit --audit-level=moderate
• New or changed behavior has unit/integration tests for new branches, fallback paths, and sanitizer boundaries

Safety

• No secrets, wallet details, hotkeys, coldkeys, user PATs, private keys, raw trust scores, private rankings, or private maintainer evidence are exposed.
• Public GitHub text stays sanitized, low-noise, and does not imply compensation guarantees or optimization tactics.
• Auth, cookie, CORS, GitHub App, Cloudflare, or session changes include negative-path tests.
• API/OpenAPI/MCP behavior is updated and tested where needed.
• UI changes use live API data or real empty/error/loading states, not production mock/demo fallbacks.
• Visible UI changes include a UI Evidence section below with JPG/JPEG or PNG screenshots arranged as organized, captioned, clickable thumbnails.
• Public docs/changelogs are updated where needed; changelogs are only edited for release-prep PRs.

Notes

• No UI changes in this PR (MCP server + CLI profile config only), so the UI Evidence section is not applicable.
• The tool wraps the existing buildGittensorConfigRecommendationResponse handler unmodified (aside from exporting it) — no changes to the underlying recommendation logic, per the issue's explicit instruction not to reimplement buildGittensorConfigRecommendation.
• Auth: uses requireRepoAccess, matching the real REST route's auth tier (no additional gate) and the precedent set by the already-shipped loopover_get_registration_readiness tool, which exposes adjacent economics-adjacent data at the same tier.
• The tool's summary line branches on report.warnings.length (not reasons.length, which is always non-empty by construction) so both the "no outstanding warnings" and "warning(s) to review" branches are genuinely reachable and are each covered by a dedicated test.

[superagent-security]

Superagent didn't find any vulnerabilities or security issues in this PR.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 95.16%. Comparing base (a211791) to head (70d6eed).
⚠️ Report is 12 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main    #6016   +/-   ##
=======================================
  Coverage   95.16%   95.16%           
=======================================
  Files         591      591           
  Lines       46934    46942    +8     
  Branches    15000    15001    +1     
=======================================
+ Hits        44664    44672    +8     
  Misses       1512     1512           
  Partials      758      758           

Flag	Coverage Δ
shard-1	43.93% <25.00%> (-0.01%)	⬇️
shard-2	36.54% <25.00%> (+<0.01%)	⬆️
shard-3	32.16% <25.00%> (+0.16%)	⬆️
shard-4	32.94% <25.00%> (+0.98%)	⬆️
shard-5	31.47% <100.00%> (-1.07%)	⬇️
shard-6	44.57% <25.00%> (-0.01%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
src/api/routes.ts	94.40% <ø> (ø)
src/mcp/server.ts	96.13% <100.00%> (+0.03%)	⬆️

[loopover-orb]

Tip

🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩🟩

✅ LoopOver review result - approve/merge recommended

_{Review updated: 2026-07-15 07:12:54 UTC}

5 files · 1 AI reviewer · no blockers · readiness 98/100 · CI green · clean

✅ Suggested Action - Approve/Merge

• safe to merge

Review summary
This PR wraps the existing buildGittensorConfigRecommendationResponse in a new read-only MCP tool loopover_get_config_recommendation, mirroring the sibling registration-readiness/label-audit tools exactly (access check via requireRepoAccess, toolResult wrapping, output schema, registration in the tools-with-output-schema test list). It exports the previously-private function, registers the tool in the repo-owner-intake profile's recommendedTools list matching that profile's stated purpose, and adds tests covering the clean/no-warnings path, the warnings path, and the access-denied path. The wiring is consistent with the established pattern and the change is narrowly scoped to this one feature.

Nits — 4 non-blocking

• src/mcp/server.ts: the summary string duplicates the 'advisory only, not a write action' phrase already stated in the tool description — consider trimming one of the two for conciseness.
• test/unit/mcp-config-recommendation.test.ts: the forbids-access test doesn't assert the tool's structuredContent/data is empty or absent on the error path, only that isError is true — worth confirming no partial config data leaks on the error response.
• Consider adding a coverage assertion or comment noting that the /* v8 ignore start */ block in src/api/routes.ts still applies now that the function is exported, since exporting could change v8's branch instrumentation boundaries.
• Double check that outputSchema optional fields (current, recommended) align with the null current value asserted in the first test — z.unknown().optional() will pass through null fine, but worth a one-line note for future readers.

Signal	Result	Evidence
Code review	✅ No blockers	1 reviewer
Linked issue	✅ Linked	#5823
Related work	✅ No active overlap found	No same-issue or scoped active PR overlap found.
Change scope	✅ 20/20	Low review scope from cached public metadata (1 linked issue).
Validation posture	✅ 25/25	PR body includes validation/test evidence.
Contributor workload	✅ 10/10	Author activity: 55 registered-repo PR(s), 45 merged, 0 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	oktofeesh1; Gittensor profile; 55 PR(s), 0 issue(s).
Gate result	✅ Passing	No configured blocker found.
Improvement	✅ Minor	risk: clean · value: minor · LLM: minor

Linked issue satisfaction

Addressed
The diff adds loopover_get_config_recommendation to src/mcp/server.ts with ownerRepoShape input, an output schema, and a handler that calls the exported buildGittensorConfigRecommendationResponse directly (exporting it from routes.ts rather than reimplementing logic), matches the described advisory/no-write semantics, and registers the tool in the repo-owner-intake profile's recommendedTools as re

Review context

• Author: oktofeesh1
• Role context: outside_contributor
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: JavaScript, MDX, Python, TypeScript
• Official Gittensor activity: 55 PR(s), 0 issue(s).
• PR-specific overlap: none found.

Contributor next steps

• Keep the PR focused and include validation evidence before maintainer review.

Signal definitions

• Related work = same linked issue, overlapping active PRs, or title/path similarity.
• Change scope = cached public metadata such as size labels, draft state, and review-burden hints.
• Validation posture = whether the PR provides enough public validation/test evidence for maintainer review.
• Contributor workload = public contributor activity and cleanup pressure, not a repo-wide quality failure.
• Contributor context = public GitHub/Gittensor identity context; non-Gittensor status is not a blocker.

🧪 Chat with LoopOver

Ask LoopOver a question about this PR directly in a comment — grounded only in the same cached, public-safe facts shown above, never a new claim.

• @loopover ask <question> answers contribution-quality Q&A with source citations and freshness.
• @loopover chat <question> answers in natural prose from cached decision-pack facts via local inference (maintainer/collaborator; read-only).
• A plain-language @loopover mention with a real question is routed to the closest matching read-only command automatically — no exact syntax required.

Full command reference: https://gittensory.aethereal.dev/docs/loopover-commands

🧪 Experimental — new and may change.

_{🟩 Safe / merged · 🟦 Advisory · 🟨 Held for review · 🟥 Blocked / closed}

---

💰 Earn for open-source contributions like this. Gittensor lets GitHub contributors earn for the work they already do — register to start earning →.

Checked by LoopOver, a quiet PR intelligence layer for OSS maintainers.

• Re-run LoopOver review

[loopover-orb]

LoopOver approves — the gate is satisfied and CI is green.