Verified place shortlist — Atom
Server Details
Verified place shortlist: declared place shortlist record checked per call.
- Status
- Healthy
- Uptime
- 42.9% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- nrupala/atom-services
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 1 tool
There is only one tool, so there is no possibility of misselection between siblings. Its scope is spelled out precisely: it audits a declared shortlist record and returns a verdict, and it explicitly disclaims live fetching, verification, recommending, and booking.
The single name is lower snake_case, domain-specific, and self-describing, with no competing conventions to clash against. The description also pre-empts a possible misreading of the word 'verified' as live verification.
A one-tool surface is thin but defensible here, because the server is a single-purpose deterministic evaluator: submit declared record, receive verdict. It nevertheless scores below a well-scoped multi-tool set, because the entire surface is one monolithic operation.
For the narrow audit-the-declared-record domain, the tool covers the six enumerated check sections, covering coverage, evidence completeness, winner/backup resolution, and freshness/uncertainty. There is no companion operation for retrieving, listing, or re-inspecting prior submissions or verdicts, leaving only a submit-and-verdict path with no persistence or read-side surface.
Available Tools
1 toolverified_place_shortlistVerified place shortlistARead-onlyIdempotentInspect
Submits a verified place shortlist record (constraint declarations, declared criterion rows, declared place rows with declared verification evidence, evaluation declarations, ranking declarations, freshness and uncertainty handling declarations, red lines) and returns a deterministic VERIFIED_PLACE_SHORTLIST_SOUND / VERIFIED_PLACE_SHORTLIST_NOT_SOUND / INSUFFICIENT_EVIDENCE verdict across six sections, including computed criterion-to-place coverage, per-row evidence completeness and winner and backup resolution checks over the declared rows, with per-check evidence. Audits the declared shortlist record only; it fetches nothing live, verifies no real-world fact and recommends or books nothing. The word verified in its name refers to the caller's declared verification discipline, not to any live verification by the atom.
Inputs: places, ranking, criteria, handling, +4 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Vendor evaluation three-way match: declared procurement record checked per call.
Statistical study design report: declared study design record checked per call.
PRD with testable acceptance criteria: declared PRD record checked per call.
Personal web presence audit: declared personal presence record checked per call.
Related MCP Servers
AlicenseNot gradedqualityCmaintenanceProvides an MCP endpoint for agents to check whether a real-world fact can be verified, covering businesses, listings, objects, and places, while refusing claims about individuals. It acts as a demand sensor that logs verification attempts, even for unfulfillable requests.MIT- FlicenseAqualityBmaintenanceEnables agents to verify claims against a real falsification ledger, querying pre-registered refutation thresholds, recorded verdicts, and verifier drift metrics instead of guessing.5-
- AlicenseAqualityBmaintenanceVerified pay-per-call catalog: factual checks of x402 agent services for AI agents.31MIT
- FlicenseNot gradedqualityAmaintenanceEnables AI assistants and researchers to verify bibliographic records against multiple metadata sources and check metadata consistency using identifier-first and explainable multi-signal matching. It supports non-destructive updates, structured provider outcomes, and JSON output for automation.-
Glama MCP Gateway
Add one secure layer between your agents and this server.