MCP Risk

Directory / server

ai.arpi/arpi-mcp

This directory entry reports an automated security scan of ai.arpi/arpi-mcp, 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 none

C 79/100 permalink

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.arpi/arpi-mcp. 1 finding
  • Registry entry: ai.arpi/arpi-mcp ↗
WARN Source repository is public and maintained §1.2
Repository health issues: no license. 5 findings
  • Repository ↗
  • Last push: 20 days ago
  • Stars: 0
  • License: none detected
  • Security policy (SECURITY.md): absent
INFO Published package is consistent and attested §1.3

No published package associated with this server (remote-only or non-npm/PyPI source).
UNVERIFIABLE Tool surface is inspectable and proportionate §2.1–§2.4

Tool surface could not be inspected (no reachable tools/list, no public package source). Per policy, unverifiability caps the overall grade.
PASS HTTPS-only endpoint §3.1
Endpoint uses HTTPS. 1 finding
  • Endpoint: https://mcp.arpi.ai/mcp
PASS Authentication required §3.2
Server rejects anonymous requests and advertises its auth scheme. 1 finding
  • WWW-Authenticate: Bearer error="invalid_token", error_description="Authentication failed. The provided bearer token is invalid, expired, or no longer recognized by the server. To resolve: clear authentication tokens in your MCP client and reconnect. Your client should automatically re-register and obtain new tokens.", resource_metadata="https://mcp.arpi.ai/.well-known/oauth-protected-resource/mcp"
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.arpi.ai/.well-known/oauth-protected-resource
INFO No known vulnerabilities (OSV.dev) §4.1

No package to query (remote-only server).
UNVERIFIABLE Server-supplied instructions free of poisoning indicators §5.1–§5.4

No server-supplied instructions or tool descriptions were obtainable to scan.

Score history

DateGradeScore
2026-07-28C79/100
2026-07-27C79/100
2026-07-27C79/100
2026-07-27C79/100
2026-07-26C79/100
2026-07-26C79/100
2026-07-26C79/100
2026-07-26D64/100
2026-07-25D58/100
2026-07-25D64/100
2026-07-25B90/100
2026-07-25B90/100
2026-07-24B90/100
2026-07-24B90/100
2026-07-24B90/100
2026-07-12D64/100
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.