Vendor evaluation three way match pack — Atom
Server Details
Vendor evaluation three-way match: declared procurement record checked per call.
- Status
- Healthy
- Uptime
- 14.3% 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
Score is being calculated.
Available Tools
1 toolvendor_evaluation_three_way_match_packVendor evaluation three way match packARead-onlyIdempotentInspect
Submits a vendor evaluation and three-way match record (spec and sourcing declarations, evaluation setup, declared vendor rows and declared criteria rows, contract and terms declarations, purchase-order discipline declarations, three-way match declarations, declared purchase-order, receipt and invoice line rows, vendor-record declarations, red lines) and returns a deterministic VENDOR_EVALUATION_AND_MATCH_SOUND / VENDOR_EVALUATION_AND_MATCH_NOT_SOUND / INSUFFICIENT_EVIDENCE verdict across seven sections, including exact recomputation of weighted vendor totals, per-line totals, cross-document quantity and unit-price matching and both grand totals over the declared rows, with per-check evidence. Audits the declared record only; it contacts no vendor, approves no payment and gives no procurement advice.
Inputs: spec, vendors, contract, criteria, +10 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
PRD with testable acceptance criteria: declared PRD record checked per call.
Mechanically reconcile supplied purchase-order lines, invoice lines and goods receipts under expl...
Negotiation preparation pack: declared preparation record checked per call.
Vendor and contract records: renewals by notice deadline, spend, contracts and approved changes.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables automated forensic auditing of public procurement tenders by parsing RFQ specifications, detecting price drift against market baselines, flagging bidder collusion risks, and enforcing human officer approval before any decision is recorded.9,324 npm1MIT
- AlicenseNot gradedqualityBmaintenanceEnables procurement officers and MCP clients to ingest tender and bid documents, run cited multi-agent evaluations with scores and risk flags, and review audit trails while preventing AI from recording award decisions.MIT
- AlicenseNot gradedqualityBmaintenanceEnables evaluation of synthetic tender requirements against supplier evidence by loading tenders, building compliance matrices, flagging unresolved risks, and preparing draft evidence packs with preserved provenance. Finalization stays blocked behind a mandatory human approval gate, so no award decision is made autonomously.MIT
- AlicenseNot gradedqualityCmaintenanceEnables users to load synthetic records from three finance systems, propose evidence-backed vendor matches by confidence tier, inspect crosswalk status, build reviewer packets, record human decisions, and run the eval gate, all without writing to source systems.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.