Evaluation report
Warnings@swarmclawai/swarmclaw · mcpe1e45f5· 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/swarmclawai/swarmclaw @ e1e45f5 — ★ 587 · TypeScript · MIT · last push 10 days ago
Manifest detected
kind=mcp slug=swarmclawai-swarmclaw · source=package.json
Slug is URL-safe
"swarmclawai-swarmclaw" matches /^[a-z0-9][a-z0-9-]{0,62}$/
Slug is unique within kind
No collision found for mcp/swarmclawai-swarmclaw
Version is semver
1.9.39
Documentation
5 passedDescription quality
20 words · 158 chars — "Build and run autonomous AI agents with OpenClaw, Hermes, multiple model provide…"
README is present and substantial
102,964 chars · 28 sections · 9 code blocks
Tags / topics declared
29 total — openclaw, crustacean, clawd, clawdbot, moltbot, file-queue (+23)
README has usage / example sections
found: Quick Start
Homepage / docs URL declared
https://www.swarmclaw.ai
Safety
2 passed1 warningDependencies: known vulnerabilitieswarn
1 high/critical advisory — @opentelemetry/[email protected] (HIGH: GHSA-q7rr-3cgh-j5r3)
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
4 passed1 warningMCP: ESM packagewarn
package.json missing "type": "module"
Modern MCP servers are ESM. Add `"type": "module"` unless you have a CJS-only reason.
MCP: launch path
bin: swarmclaw · scripts.start
MCP: @modelcontextprotocol/sdk in dependencies
pinned at "^1.29.0"
MCP: SDK version pinned
pinned at "^1.29.0"
MCP: server surface
0 tools
Maintenance
3 passedRecent activity
last push 10 days ago
Tests detected
2 test directories · 410 test files
CI configuration detected
GitHub Actions (3 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.