MCP Risk

Directory / server

ai.bowmark/bowmark

This directory entry reports an automated security scan of ai.bowmark/bowmark, 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 69/100 permalink

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.bowmark/bowmark. 1 finding
  • Registry entry: ai.bowmark/bowmark ↗
PASS Source repository is public and maintained §1.2
Active repository with a license. 5 findings
  • Repository ↗
  • Last push: 10 days ago
  • Stars: 0
  • License: MIT
  • Security policy (SECURITY.md): absent
FAIL Published package is consistent and attested §1.3
Integrity concerns: package repository field does not match the claimed source repo; package is only 24 days old. 6 findings
  • Package: bowmark-mcp@1.0.2 ↗
  • Ecosystem: npm
  • Age: 24 days
  • Weekly downloads: 170
  • Repo field matches source repo: false
  • Build-provenance attestation: present
PASS Tool surface is inspectable and proportionate §2.1–§2.4
3 tool(s) enumerated; no high-risk capability signals. 2 findings
  • Tools exposed: 3
  • Detected capabilities: none
PASS HTTPS-only endpoint §3.1
Endpoint uses HTTPS. 1 finding
  • Endpoint: https://api.bowmark.ai/mcp?s=r
WARN Authentication required §3.2

Server answers anonymous requests (HTTP 200). Acceptable only for deliberately public, read-only (Low) servers.
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://api.bowmark.ai/.well-known/oauth-protected-resource
PASS No known vulnerabilities (OSV.dev) §4.1

No advisories on record for bowmark-mcp @1.0.2 (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
  • ask description: oversized: 3369 chars (limit 2048)

Score history

DateGradeScore
2026-07-28C69/100
2026-07-27D59/100
2026-07-27D59/100
2026-07-27D59/100
2026-07-27D59/100
2026-07-26D59/100
2026-07-26D59/100
2026-07-26D59/100
2026-07-26F44/100
2026-07-25D50/100
2026-07-25D50/100
2026-07-25D50/100
2026-07-25D50/100
2026-07-24D50/100
2026-07-24D50/100
2026-07-24F44/100
2026-07-12D59/100
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.