feat(mcp): register loopover_mark_notifications_read as a local stdio tool

[real-venus]

Summary

Closes #7762 — loopover_mark_notifications_read has a remote MCP tool (src/mcp/server.ts) and a notifications-read CLI command, but no local stdio MCP tool registration. #6745 added the REST route + CLI but never the matching stdio tool, so a self-host operator using the local MCP server (not the CLI or remote MCP) couldn't call it.

What changed (packages/loopover-mcp/bin/loopover-mcp.ts)

• A registerStdioTool("loopover_mark_notifications_read", …) block, placed next to the other contributor-scoped tools, following the existing sibling pattern exactly.
• Reuses the same postMarkNotificationsRead helper (POST /v1/contributors/:login/notifications/read) the notifications-read CLI already calls — no duplicated HTTP logic.
• login resolves from the arg / active session / LOOPOVER_LOGIN (same as the CLI and the loopover_get_pr_ai_review_findings sibling); ids is optional (omit to mark every delivered notification read).
• Description centralized via stdioToolDescription(...) + a STDIO_TOOL_DESCRIPTORS entry (category: "utility", matching the remote tool), not hardcoded inline.

Testing / coverage

• test/unit/mcp-cli-mark-notifications-read.test.ts: drives the tool in-process (the loopover_plan_repo_issues has no REST route, CLI command, or local stdio MCP tool #7764 isProcessEntrypoint guard + InMemoryTransport, mirroring mcp-cli-repo-focus-manifest.test.ts) so the registration + handler get real Codecov-measured coverage — a subprocess spawn can't be v8-instrumented. Covers mark-all (empty body), explicit ids forwarding, and the no-login throw branch (so the login ?? … fallback chain and the guard are fully branch-covered).
• Tool-count invariant in test/unit/mcp-tool-rename-aliases.test.ts bumped 89 → 90.

No REST/OpenAPI/CLI-surface change (the route and notifications-read CLI already exist) — ui:openapi:check, command-reference:check, docs/manifest drift all clean; build:mcp clean.

[superagent-security]

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

[loopover-orb]

Tip

✅ LoopOver review result - approve/merge recommended

_{Review updated: 2026-07-21 21:24:16 UTC}

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

✅ Suggested Action - Approve/Merge

• safe to merge

Review summary
This PR adds a `loopover_mark_notifications_read` local stdio tool mirroring the existing remote MCP tool and CLI command, closing #7762. The implementation follows the established `registerStdioTool` pattern exactly (login fallback chain, `stdioToolDescription` + `STDIO_TOOL_DESCRIPTORS` entry), reuses the existing `postMarkNotificationsRead` helper rather than duplicating HTTP logic, and ships in-process tests that exercise both the mark-all and explicit-ids paths plus the no-login throw branch. The tool-count bump (89→90) is correctly reflected in the invariant test.

Nits — 6 non-blocking

• I can't see the definition/import of `postMarkNotificationsRead` in the visible diff or the truncated full-file excerpt (the middle ~274K chars are omitted) — please confirm it's actually defined/imported in this file rather than assuming it from the PR description.
• packages/loopover-mcp/bin/loopover-mcp.ts:2344 — the handler signature `async ({ login, ids }: any)` matches the file's existing loose-typing convention for handlers, so it's acceptable, but it'd be nice to type it against `markNotificationsReadShape` if the file ever tightens its typing pass.
• test/unit/mcp-cli-mark-notifications-read.test.ts:27 — `LOOPOVER_API_TOKEN = "in-process-token"` is a hardcoded fixture string flagged by secret-scanning; it's a harmless test literal (matches the sibling `mcp-cli-repo-focus-manifest.test.ts` pattern presumably), but worth a quick glance to confirm no real credential ever lands in this file.
• The PR description promises `command-reference:check`/docs/manifest drift is clean, but that isn't independently verifiable from the diff alone — worth double-checking CI output covers those specific checks (CI status here just says 'validate' passed, not which sub-checks ran).
• Add a one-line assertion in the new test that `tool?.inputSchema` (or the zod shape) accepts an `ids` array of at least one item, to lock in the shape contract alongside the description assertion already present.
• Possible secret-shaped assignment in the diff (generic_secret_assignment) — Verify the value is not a real credential.

Decision drivers

• ✅ Code review — No blockers (1 reviewer)
• ✅ Gate result — Passing (No configured blocker found.)

Context & advisory signals — never blocks the verdict

Signal	Result	Evidence
Linked issue	✅ Linked	#7762
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: 111 registered-repo PR(s), 51 merged, 19 issue(s).
Contributor context	✅ Confirmed Gittensor contributor	real-venus; Gittensor profile; 111 PR(s), 19 issue(s).
Improvement	✅ Minor	risk: clean · value: minor

Linked issue satisfaction

Addressed
The diff adds a registerStdioTool block for loopover_mark_notifications_read mirroring the sibling pattern, reuses postMarkNotificationsRead (the same helper the CLI's notifications-read command calls) rather than duplicating HTTP logic, and centralizes the description via stdioToolDescription/STDIO_TOOL_DESCRIPTORS, with accompanying tests and tool-count updates.

Review context

• Author: real-venus
• Role context: outside_contributor
• Public audience mode: oss maintainer
• Lane context: Repository is configured for direct PR review.
• Public profile languages: TypeScript, JavaScript, Python, Rust, CSS, MDX, Svelte, Swift
• Official Gittensor activity: 111 PR(s), 19 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://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

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 81.84%. Comparing base (bc042ed) to head (18a8ced).
⚠️ Report is 2 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #7950      +/-   ##
==========================================
+ Coverage   79.50%   81.84%   +2.34%     
==========================================
  Files         735       91     -644     
  Lines       75452    23694   -51758     
  Branches    22952     4547   -18405     
==========================================
- Hits        59986    19393   -40593     
+ Misses      12710     4105    -8605     
+ Partials     2756      196    -2560     

Flag	Coverage Δ
shard-1	11.59% <100.00%> (-42.63%)	⬇️
shard-2	0.00% <0.00%> (-53.79%)	⬇️
shard-3	0.00% <0.00%> (?)

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	11.59% <100.00%> (-2.50%)	⬇️

... and 644 files with indirect coverage changes

[real-venus]

@JSONbored
Wating to merge.