MCP Risk

Directory / server

ai.autonomad/travel

This directory entry reports an automated security scan of ai.autonomad/travel, scanned 2026-07-28. Trust grade C rates provenance, transport, known vulnerabilities and instruction integrity; capability risk is reported separately, not folded into the grade.

registry.modelcontextprotocol.io, scanned 2026-07-28, tool surface via remote-tools-list

C 65/100 permalink

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.autonomad/travel. 1 finding
  • Registry entry: ai.autonomad/travel ↗
FAIL Source repository is public and maintained §1.2

Claimed source repository does not exist (or is private).
WARN Published package is consistent and attested §1.3
Minor integrity gaps: no npm provenance attestation. 6 findings
  • Package: autonomad-travel@1.4.1 ↗
  • Ecosystem: npm
  • Age: 88 days
  • Weekly downloads: 67
  • Repo field matches source repo: true
  • Build-provenance attestation: absent
PASS Tool surface is inspectable and proportionate §2.1–§2.4
8 tool(s) enumerated; no high-risk capability signals. 2 findings
  • Tools exposed: 8
  • Detected capabilities: none
PASS HTTPS-only endpoint §3.1
Endpoint uses HTTPS. 1 finding
  • Endpoint: https://mcp.autonomad.ai/mcp
UNVERIFIABLE Authentication required §3.2

Endpoint rejected the probe (HTTP 400); whether it requires authentication could not be determined.
WARN OAuth protected-resource metadata published §3.3
No protected-resource metadata found - clients cannot discover the authorization server per spec. 1 finding
  • Checked: https://mcp.autonomad.ai/.well-known/oauth-protected-resource
PASS No known vulnerabilities (OSV.dev) §4.1

No advisories on record for autonomad-travel @1.4.1 (npm).
WARN Server-supplied instructions free of poisoning indicators §5.1–§5.4
1 suspicious indicator(s) found in server-supplied instructions, tool descriptions, or schemas. 1 finding
  • create_booking_intent description: oversized: 3085 chars (limit 2048)

Score history

DateGradeScore
2026-07-28C65/100
2026-07-27C65/100
2026-07-27C65/100
2026-07-27C65/100
2026-07-27C65/100
2026-07-26C65/100
2026-07-26C65/100
2026-07-26C65/100
2026-07-26C70/100
2026-07-25C70/100
2026-07-25C70/100
2026-07-25C78/100
2026-07-25C78/100
2026-07-24C78/100
2026-07-24C78/100
2026-07-24C78/100
2026-07-12C70/100
What this grade covers
  • Provenance & supply-chain integrity (§1)
  • Tool surface & capability risk (§2)
  • Transport & authentication (§3)
  • Known CVEs via OSV.dev (§4)
  • Instruction/tool poisoning patterns (§5)

Limitations: pattern-based only (no semantic injection detection), static npm analysis (live server instructions not retrieved for package-only scans), single-server scope (no cross-server toxic flow analysis). See the full policy.

Methodology: MCP Server Security Policy. Unfamiliar term? See the glossary.