feat(mcp): add remote + stdio surfaces for loopover_get_gate_config_effective

[kai392]

Summary

• Closes loopover_get_gate_config_effective has a REST route but no remote MCP tool or local stdio MCP tool #7800: register loopover_get_gate_config_effective on the remote MCP server and local stdio bin (thin mirror of GET /v1/repos/:owner/:repo/gate-config/effective).
• Same canAccessRepo / MCP_READ_REPO_ALLOWLIST boundary as PR reviewability; returns effective thresholds + shadowPending.
• Declares outputSchema so mcp-output-schemas (chore(mcp): add outputSchema to tools that lack it #550) passes (fix for closed feat(mcp): add remote + stdio surfaces for loopover_get_gate_config_effective #7923).
• Pins stdio tool discovery count 84 → 85 (after feat(mcp): add remote + stdio surfaces for loopover_get_upstream_ruleset #7921 upstream_ruleset).

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
• vitest mcp-output-schemas + mcp-gate-config-effective + mcp-cli-gate-config-effective + mcp-tool-rename-aliases; codecov/patch requires ≥99% coverage of the lines AND branches you changed.
• npm run test:workers
• npm run build:mcp (local)
• 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

If any required check was skipped, explain why:

• Full local matrix deferred to CI; exercised the failing suite from feat(mcp): add remote + stdio surfaces for loopover_get_gate_config_effective #7923 plus the new tool's unit coverage and build:mcp.

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. SVG screenshots are not used as review evidence. Review-only screenshots or recordings are not committed to the repository.
• Public docs/changelogs are updated where needed; changelogs are only edited for release-prep PRs.

UI Evidence

N/A — MCP/API only; no visible UI changes.

Notes

• Fresh PR after feat(mcp): add remote + stdio surfaces for loopover_get_gate_config_effective #7923 was auto-closed for missing outputSchema on validate-tests.
• One-shot PR: will not push follow-up commits onto this branch after open.

Made with Cursor

[superagent-security]

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

[codecov]

Codecov Report

❌ Patch coverage is 29.41176% with 12 lines in your changes missing coverage. Please review.
✅ Project coverage is 80.80%. Comparing base (a97dd18) to head (85adc68).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
src/mcp/server.ts	14.28%	12 Missing ⚠️

❗ There is a different number of reports uploaded between BASE (a97dd18) and HEAD (85adc68). Click for more details.

HEAD has 1 upload less than BASE

Flag	BASE (a97dd18)	HEAD (85adc68)
shard-3	1	0

Additional details and impacted files

@@             Coverage Diff             @@
##             main    #7925       +/-   ##
===========================================
- Coverage   91.77%   80.80%   -10.97%     
===========================================
  Files         731       90      -641     
  Lines       74887    24411    -50476     
  Branches    22847     4698    -18149     
===========================================
- Hits        68726    19725    -49001     
+ Misses       5083     4444      -639     
+ Partials     1078      242      -836     

Flag	Coverage Δ
shard-1	22.80% <29.41%> (-37.44%)	⬇️
shard-2	21.80% <17.64%> (-24.35%)	⬇️
shard-3	?

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

Files with missing lines	Coverage Δ
packages/loopover-mcp/bin/loopover-mcp.ts	13.66% <100.00%> (+0.07%)	⬆️
src/mcp/server.ts	56.54% <14.28%> (-40.00%)	⬇️

... and 641 files with indirect coverage changes

[loopover-orb]

Caution

🛑 LoopOver review result - reject/close recommended

_{Review updated: 2026-07-21 18:32:43 UTC}

7 files · 1 AI reviewer · 1 blocker · CI failing · dirty

🛑 Suggested Action - Reject/Close

Review summary
This PR registers loopover_get_gate_config_effective as a thin MCP mirror (remote + stdio) of the existing REST gate-config/effective route, reusing loadOverride/loadShadowOverride and the same canAccessRepo boundary as other maintainer tools, and bumps the tool-count pin from 84 to 85. The wiring looks consistent with sibling tools (e.g. activation_preview), the forbidden-path and live/shadow-override tests exercise real branches, and outputSchema correctly makes fields optional to cover both the forbidden shape and the success shape. The codecov/patch failure (29.41% vs 99% target) is the main open issue — likely from the sizable descriptor/registration boilerplate in loopover-mcp.ts not being fully exercised, though the branch is also 1 commit behind default and that could be a contributing factor.

Blockers

• codecov/patch failed at 29.41% vs the 99% target — significant chunks of the new registration/proxy code in packages/loopover-mcp/bin/loopover-mcp.ts and/or src/mcp/server.ts are apparently untested despite the two new test files, and this must be resolved (either genuine missing coverage or confirmed as a stale-branch artifact) before merge.

Nits — 6 non-blocking

• src/mcp/server.ts: the forbidden-path response omits `effective`/`shadowPending` entirely rather than nulling them, which is fine given the optional outputSchema, but consider documenting that callers must branch on `status` before reading `effective` (easy to trip up a consumer expecting a stable shape).
• packages/loopover-mcp/bin/loopover-mcp.ts:1572 introduces an explicit `any` annotation (`async ({ owner, repo }: any) =>`) — the surrounding stdio tools may follow this pattern, but consider typing against the inferred input schema instead.
• test/unit/mcp-cli-gate-config-effective.test.ts:37 sets `LOOPOVER_API_TOKEN = "in-process-token"`, a hardcoded fixture token; verify this matches the convention used by sibling test files (e.g. mcp-cli-activation-preview.test.ts) and isn't a real credential pattern.
• Both new test files and the diff add real branch coverage (forbidden, empty override, live+shadow) which is good, but the low patch-coverage number suggests other changed lines (e.g. descriptor entries, category map entry) aren't being counted — worth double-checking the coverage report to confirm it's boilerplate and not logic.
• Re-run codecov locally scoped to src/** for this diff to see exactly which lines are uncovered before assuming it's just boilerplate.
• Possible secret-shaped assignment in the diff (generic_secret_assignment) — Verify the value is not a real credential.

Why this is blocked

• codecov/patch failed at 29.41% vs the 99% target — significant chunks of the new registration/proxy code in packages/loopover-mcp/bin/loopover-mcp.ts and/or src/mcp/server.ts are apparently untested despite the two new test files, and this must be resolved (either genuine missing coverage or confirmed as a stale-branch artifact) before merge.

📋 Copy for AI agents — paste into your coding agent

Fix the following blocker(s) from this PR review:

1. codecov/patch failed at 29.41% vs the 99% target — significant chunks of the new registration/proxy code in packages/loopover-mcp/bin/loopover-mcp.ts and/or src/mcp/server.ts are apparently untested despite the two new test files, and this must be resolved \(either genuine missing coverage or confirmed as a stale-branch artifact\) before merge.

CI checks failing

• codecov/patch — 29.41% of diff hit (target 99.00%)

Decision drivers

• ❌ Code review — 1 blocker (1 reviewer)
• ❌ Gate result — Blocking (Repo-configured hard blocker found.)

Context & advisory signals — never blocks the verdict

Signal	Result	Evidence
Linked issue	✅ Linked	#7800, #7923
Related work	⚠️ 1 scoped overlap	Top overlaps are listed below; lower-confidence bulk is hidden.
Change scope	❌ 8/20	High review scope from cached public metadata (2 linked issues).
Validation posture	✅ 25/25	PR body includes validation/test evidence.
Contributor workload	✅ 10/10	Author activity: 47 registered-repo PR(s), 27 merged, 0 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	kai392; Gittensor profile; 47 PR(s), 0 issue(s).
Improvement	✅ Minor	risk: clean · value: minor · LLM: moderate

Linked issue satisfaction

Addressed
The diff registers loopover_get_gate_config_effective as a remote MCP tool (ownerRepoShape input, "maintainer" category, wired to loadOverride/loadShadowOverride, returning the exact repoFullName/effective/shadowPending shape) and as a local stdio tool proxying GET .../gate-config/effective, with no new REST route or human CLI verb, matching all stated deliverables.

Review context

• Author: kai392
• Role context: outside_contributor
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: JavaScript, Kotlin, Perl, TypeScript, Vue
• Official Gittensor activity: 47 PR(s), 0 issue(s).
• Related work: Titles/paths share 7 meaningful terms. (PR #7926)

Contributor next steps

• Start here: Review top overlaps.
• Then work through the remaining 2 steps in the Signals table above.

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://loopover.ai/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 is closing this pull request on the maintainer's behalf (CI is failing (codecov/patch); conflicts with the base branch — resolve and open a fresh PR; AI reviewers agree on a likely critical defect: codecov/patch failed at 29.41% vs the 99% target — significant chunks of the new registration/proxy code in packages/loopover-mcp/bin/loopover-mcp.ts and/or src/mcp/server.ts are apparently untested despite the two new test files, and this must be resolved (either genuine missing coverage or confirmed as a stale-branch artifact) before merge.). This is an automated maintenance action — to pursue this change, please open a new pull request with the issues resolved. Closed PRs may be analyzed later to improve review accuracy, but they are not automatically reopened or re-reviewed.