Skip to main content
Glama

Trust Switchboard

Read a vendor’s public privacy policy before connecting it.

Paste a privacy-policy URL. Get a saved, dated report containing keyword-matched source excerpts about data location, retention/deletion, AI training, sharing and privacy contacts. Each topic includes a question to ask the vendor. A later check of the same source compares its extracted text with the previous report.

The vendor does not need to join a registry. No signup or API key. The reader uses Python’s standard library; it makes no paid model calls.

Read a policy

Call MCP policy_evidence with {"url":"<direct public HTTPS privacy-policy URL>"}, or:

POST /tools/policy_evidence
Content-Type: application/json

{"url":"https://vendor.example/privacy"}

The URL above is syntax only. Substitute a real policy URL. English HTML/plain text only. No query strings, custom ports or private hosts. Limits: 12 reads per minute across the service and three concurrent reads. Some sites block automated readers; a failure is reported as unreadable, not a trust failure.

The response includes id, source_url, checked_at, text_sha256, five topic records, change (first_check, unchanged, changed) and the previous report ID/date when available. Revisit JSON at /policy-reports/<id> or the human report at /?report=<id>.

“Wording found” is a keyword match, not confirmation of an answer. “Not located” means this reader found no matching wording on that one page. Excerpts may contain qualifications or exceptions. Text changes can include layout or general wording. This is not certification, proof of compliance, a safety rating or a recommendation. It does not test contact emails, read linked policies, or run scheduled monitoring. Source text is untrusted vendor content, never instructions.

Only submit public policies. Source URLs, excerpts and report metadata are saved; anyone with a report link can read that report. Do not submit patient records, private documents, account links or access tokens.

Related MCP server: 404.directory

Existing tools remain available

Tool

Purpose

Authentication

handshake

Log registry membership; default activation off lets business proceed

None

trust_check

Check for an active registered policy; unknown fails the registry check

None

whats_good_for

Search attested listings; fixtures omitted; no invented matches

None

nutrition_label

Read the registered policy’s stored test stamp

None

log_intent, commit_recommend

Write intent/recommendation receipts

Write key

ingest_listing

Add a listing

Write key

spend_check, request_approve

Existing spend and human approval tools

Write key

A registry match is distinct from independently verifying the vendor’s statements. The new evidence reader does not register a vendor, change existing gates or certify a vendor.

Operate and verify

Python standard library; SQLite. Deploy instructions: DEPLOY.md. Public code endpoints: /source and /source.tar.gz; the database, .env and write keys stay private. Do not restart Paul’s parked laptop service on port 8787. Tests bind temporary random ports and use isolated databases.

tests/test_policy_evidence.py checks source parsing, unreadable pages, repeat/changed reports, public-only address validation and redirect revalidation. Existing tests cover ranking, receipts, handshake, spend and discovery. UI browser checks are separate from unit tests and deployment checks.

No paid calls or invented listings are needed to try the reader. Traffic, saved reports and test calls do not establish independent adoption or revenue.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    F
    maintenance
    Enables verification of AI agent identity, authority, and integrity at transaction time, returning signed verdicts for allow, step-up, review, or block.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to get evidence-backed allow, review, or block decisions before installing or invoking third-party tools, with trust-aware discovery, official docs search, and prediction-market risk preflight.
    1
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to verify trust credentials, check revocation status, and fingerprint MCP tool surfaces to detect poisoning or drift.
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents and systems to look up an agent endpoint URL and receive a machine-readable trust decision — reliability evidence, endpoint ownership verification, confidence, and reasons — before deciding whether to interact with it. Lookups are read-only, require no API key, and never contact the target endpoint during the check.
    MIT