MCP Risk

Directory / server

ai.i18nagent/i18n-agent

This directory entry reports an automated security scan of ai.i18nagent/i18n-agent, scanned 2026-07-28. Trust grade A 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

A 94/100 permalink

Automated checks

StatusCheckPolicyResult
PASS Listed on the official MCP registry §1.1
Listed on registry.modelcontextprotocol.io as ai.i18nagent/i18n-agent. 1 finding
  • Registry entry: ai.i18nagent/i18n-agent ↗
PASS Source repository is public and maintained §1.2
Active repository with a license. 5 findings
  • Repository ↗
  • Last push: 69 days ago
  • Stars: 0
  • License: MIT
  • Security policy (SECURITY.md): absent
WARN Published package is consistent and attested §1.3
Minor integrity gaps: no npm provenance attestation. 6 findings
  • Package: @i18n-agent/mcp-client@1.16.3 ↗
  • Ecosystem: npm
  • Age: 334 days
  • Weekly downloads: 77
  • 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: filesystem, 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. 9 findings
  • filesystem (filesystem write/delete): lib/config-writer.js
  • filesystem (fs module import): lib/config-writer.js
  • network-egress (outbound network calls): i18n-agent.js
  • process-execution (child process execution): install.js
  • process-execution (child process module import): install.js
  • process-execution (child process execution): lib/verifier.js
  • process-execution (child process module import): lib/verifier.js
  • network-egress (outbound network calls): lib/verifier.js
  • Detected capabilities: filesystem, network-egress, process-execution
PASS HTTPS-only endpoint §3.1
Endpoint uses HTTPS. 1 finding
  • Endpoint: https://mcp.i18nagent.ai/mcp
PASS Authentication required §3.2
Server rejects anonymous requests and advertises its auth scheme. 1 finding
  • WWW-Authenticate: Bearer resource_metadata="https://mcp.i18nagent.ai/.well-known/oauth-protected-resource"
PASS OAuth protected-resource metadata published §3.3
Publishes /.well-known/oauth-protected-resource per the June 2025 authorization spec. 1 finding
  • Authorization server: https://app.i18nagent.ai
PASS No known vulnerabilities (OSV.dev) §4.1

No advisories on record for @i18n-agent/mcp-client @1.16.3 (npm).
PASS Server-supplied instructions free of poisoning indicators §5.1–§5.4

No poisoning indicators found across 71 server-supplied text item(s).

Score history

DateGradeScore
2026-07-28A94/100
2026-07-27A94/100
2026-07-27A94/100
2026-07-26A94/100
2026-07-26A94/100
2026-07-25D53/100
2026-07-25D50/100
2026-07-25D50/100
2026-07-25D53/100
2026-07-24D53/100
2026-07-24D53/100
2026-07-13D53/100
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.