Relational memory substrate for AI agents with MCP tools, identity continuity, and self-hosted persistence.
- capability exposureinferred+35
- tool safetyinferred+2
- trust mitigatorsmixed−3
inferredmixed
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 14m ago · see ecosystem CVEs →
- B · 25 → B · 34
No known CVEs for this server.
- lowexfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit 0dd97da · analyzer v17 · 3d ago
skills & prompt files 1
danger signals2
- suspicious endpointapi.telegram.orgfalcoschaefer99-eng-muse-brain-0dd97da/runner/src/notifiers/telegram.ts:42
const response = await fetch(`https://api.telegram.org/bot${this.botToken}/sendMessage`, { - suspicious endpointapi.telegram.orgfalcoschaefer99-eng-muse-brain-0dd97da/runner/src/telegram-voice-bridge.ts:90
const response = await fetch(`https://api.telegram.org/bot${botToken}/${method}`, {
[](https://mcpobservatory.com/servers/github:falcoschaefer99-eng/muse-brain/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 falcoschaefer99-eng.