Evaluation report
Warnings@agenticmail/mcp · mcp4a0e0f6· 3 months ago
Every check MetaHub ran on this artifact, grouped by area. Static checks run on the source at publish time; behavioral checks run the artifact in a sandbox and judge what it actually does.
Structural
5 passedRepository is reachable
https://github.com/agenticmail/agenticmail @ 4a0e0f6 — ★ 166 · TypeScript · MIT · last push 3 weeks ago
Manifest detected
kind=mcp slug=agenticmail-mcp · path=packages/mcp · source=package.json
Slug is URL-safe
"agenticmail-mcp" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/agenticmail-mcp
Version is semver
0.9.29
Documentation
5 passedDescription quality
16 words · 100 chars — "MCP server for AgenticMail — give any AI client real email, SMS, and phone call-…"
README is present and substantial
76,102 chars · 19 sections · 26 code blocks
Tags / topics declared
21 total — mcp, email, sms, phone, ai, ai-agent (+15)
README has usage / example sections
found: Quick Start
Homepage / docs URL declared
https://github.com/agenticmail/agenticmail
Safety
2 passed1 warningDependencies: known vulnerabilitieswarn
4 high/critical advisories — @modelcontextprotocol/[email protected] (HIGH: GHSA-345p-7cg4-v4c7) · @modelcontextprotocol/[email protected] (HIGH: GHSA-8r9q-7v3j-jr4g) (+2)
Update the affected packages, then re-publish. (`npm audit` shows the same data locally.)
LICENSE file at repo root
LICENSE
No sensitive files in the repo
scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found
Kind-specific
5 passedMCP: launch path
bin: agenticmail-mcp
MCP: @modelcontextprotocol/sdk in dependencies
pinned at "^1.12.0"
MCP: SDK version pinned
pinned at "^1.12.0"
MCP: ESM package
"type": "module"
MCP: server surface
0 tools
Maintenance
3 passedRecent activity
last push 3 weeks ago
Tests detected
8 test directories · 84 test files
CI configuration detected
GitHub Actions (4 workflows)
Behavioral
This artifact hasn't produced behavioral results yet: the evaluation sandbox couldn't run it (it may need credentials we don't provide, or a build our environment doesn't support). That's a limitation of our environment, not a verdict on the artifact.