MCP Risk

Directory / server

ai.fodda/mcp-server

This directory entry reports an automated security scan of ai.fodda/mcp-server, scanned 2026-07-28. Trust grade B 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 package-source

B 83/100 permalink

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.fodda/mcp-server. 1 finding
  • Registry entry: ai.fodda/mcp-server ↗
WARN Source repository is public and maintained §1.2
Repository health issues: no license. 5 findings
  • Repository ↗
  • Last push: 13 days ago
  • Stars: 1
  • License: none detected
  • Security policy (SECURITY.md): absent
WARN Published package is consistent and attested §1.3
Minor integrity gaps: no npm provenance attestation. 6 findings
  • Package: fodda-mcp@1.32.1 ↗
  • Ecosystem: npm
  • Age: 161 days
  • Weekly downloads: 111
  • Repo field matches source repo: true
  • Build-provenance attestation: absent
PASS Tool surface is inspectable and proportionate §2.1–§2.4
Package source scanned. Capabilities detected: network-egress, process-execution. Reported as capability risk (§2.4); whether each is essential to the server's stated purpose is §2.3 and remains a manual judgement. 5 findings
  • network-egress (outbound network calls): dist/catalogCache.js
  • network-egress (outbound network calls): dist/pricingCache.js
  • process-execution (child process execution): dist/src/verify_hmac.js
  • process-execution (child process module import): dist/src/verify_hmac.js
  • Detected capabilities: network-egress, process-execution
PASS HTTPS-only endpoint §3.1
Endpoint uses HTTPS. 1 finding
  • Endpoint: https://mcp.fodda.ai/sse
UNVERIFIABLE Authentication required §3.2

No MCP endpoint responded at this URL (HTTP 404); authentication could not be probed.
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.fodda.ai/.well-known/oauth-protected-resource
PASS No known vulnerabilities (OSV.dev) §4.1

No advisories on record for fodda-mcp @1.32.1 (npm).
PASS Server-supplied instructions free of poisoning indicators §5.1–§5.4

No poisoning indicators found across 41 server-supplied text item(s).

Score history

DateGradeScore
2026-07-28B83/100
2026-07-27C69/100
2026-07-27C69/100
2026-07-26C69/100
2026-07-25F42/100
2026-07-25F38/100
2026-07-25F38/100
2026-07-25F38/100
2026-07-24F42/100
2026-07-24F38/100
2026-07-24F38/100
2026-07-13F43/100
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.