Skip to main content
Glama

Product Recall for Agents

Server Details

Recall for agents: lot genealogy, exposure tracing, attested remedy. Containment is not remedy.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-03-26
URL
ChatGPT
–
Claude
–

TDQS

C2.7/5.0

Scored across 6 tools

Disambiguation4/5

Most tools target distinct actions: issue_recall, record_exposure, exposure_query, and link_output are clearly separated by verb and resource. However, attest_remedy (attest remedy with proof of non-use) and completion (attested completion for a recall) both concern attestation of recall closure and could be confused for one another.

Naming Consistency4/5

Five of six tools follow a consistent snake_case verb_noun pattern (issue_recall, record_exposure, exposure_query, link_output, attest_remedy). The lone exception, 'completion', is a bare noun that breaks the pattern but remains readable.

Tool Count5/5

Six tools is well-scoped for a focused recall-lifecycle server, and each tool maps to a distinct step (issue, expose, link, attest, complete, query). No redundant or filler tools.

Completeness3/5

The surface covers issuing a recall, recording/querying exposure, linking outputs, and attesting completion, which is a reasonable lifecycle. But there is no read/list tool to retrieve an existing recall's status or details, and no way to update or cancel a recall, leaving notable gaps.

Available Tools

6 tools
attest_remedyCInspect

Attest remedy with proof of non-use / P97 omission certificate

Inputs: proof, recall_id.

completionDInspect

Attested completion for a recall

Inputs: recall_id.

exposure_queryCInspect

Exposure query $0.01 (first free once per account AND wallet; fleet covers)

Inputs: no named parameters.

issue_recallCInspect

Issue signed severity-classed recall ($49 base band, scaled above 100 exposed operators)

Inputs: lot_id, reason, severity.

record_exposureBInspect

Record load-time exposure to a lot (deduped, hash-only)

Inputs: agent, lot_id, run_id.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Verified memory for AI agents — agents propose memories that are quarantined until verified against evidence, and recall() returns only trusted, fresh, and in-scope facts, preventing poisoned or hallucinated data from spreading.
      7 npm
      1
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      First-line incident triage you can trust: ranked root-cause hypotheses where every claim cites a real evidence handle — and the agent abstains rather than guess.
      1
      1
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources