Trust-aware Nostr MCP server for AI agents and humans. Verification, proximity, and access woven into every interaction.
- capability exposure inferred + 35
- tool safety inferred + 17
- trust mitigators mixed − 11
inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 38s ago · see ecosystem CVEs →
- C · 36 → C · 41
- B · 29 → C · 36
- C · 36 → B · 29
No known CVEs for this server.
- high dangerous code
credential logged in 1 file(s)
- medium toxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
- low dangerous code
env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (forgesworn-bray-c3f415d/site/demos
analyzed commit c3f415d · analyzer v28 · 2d ago
skills & prompt files 3
- agent-rules forgesworn-bray-c3f415d/.cursorrules
- agent-rules forgesworn-bray-c3f415d/AGENTS.md
- agent-rules forgesworn-bray-c3f415d/CLAUDE.md
danger signals5
- suspicious endpoint 172.32.0.1 forgesworn-bray-c3f415d/test/validation.test.ts :35
expect(() => validatePublicUrl('http://172.32.0.1')).not.toThrow() - suspicious endpoint 169.254.169.254 (cloud metadata) forgesworn-bray-c3f415d/test/validation.test.ts :40
expect(() => validatePublicUrl('http://169.254.169.254')).toThrow(/private/) - suspicious endpoint 100.0.0.1 forgesworn-bray-c3f415d/test/validation.test.ts :57
expect(() => validatePublicUrl('http://100.0.0.1')).not.toThrow() - suspicious endpoint 100.128.0.1 forgesworn-bray-c3f415d/test/validation.test.ts :58
expect(() => validatePublicUrl('http://100.128.0.1')).not.toThrow() - credential in logs credential in log forgesworn-bray-c3f415d/site/demos/demo-phoenixd/nwc-bridge.mjs :59
console.log(`CLIENT_SECRET=${bytesToHex(clientSecret)}`)
[](https://mcpobservatory.com/servers/github:forgesworn/bray/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of forgesworn.