Edgehound
by Energixe·
io.github.Energixe/edgehound-mcp·v1.1.0Writes adversarial test suites for AI-built code. Your agent's test engineer.
A97/100grade A
Adoption
Not measured yet
Usage numbers are collected on the next scan
Reviews
Write oneNobody has reviewed Edgehound yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.2 · 2026-09-18 · same rubric, same numbers if you re-run it
no findings
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 1273ms (auth required)20/20
- Tool poisoningonly the listing description was available15/15
- Auth qualityOAuth resource metadata advertised on 40115/15
- Maintenancelast push 1 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 97/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Install directly
claude mcp add --transport http edgehound-mcp https://gauntlet.mcpize.run/mcp
Alternatives to Edgehound
Same job, ranked by rating then adoption.
Context by FulcraConnect your Fulcra Context personal datastore: access your metrics, events, agent data and morenot reviewed—A- IWEMarkdown knowledge base as agent memory. Runs against the notes directory it is started in.not reviewed—A
- Agent CommsCross-harness communication mesh for LLM agents — rooms, DMs, presence, and visibility over TCPnot reviewed—A
- SanityDirect access to your Sanity projects (content, datasets, releases, schemas) and agent rulesnot reviewed—A
- phi-guard-mcpLocal-first PHI detection for source code, LLM prompts, logs, and analyticsnot reviewed—A