Local-first MCP memory server. Indexes Claude Code/Cowork/Telegram chats; any MCP-compatible AI agent (Cursor, Cline, Continue) can search them.
- capability exposureinferred+26
- tool safetyinferred+14
- 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 9m ago · see ecosystem CVEs →
No known CVEs for this server.
- hightoxic flow (lethal trifecta)
lethal trifecta reachable across this server's tools: private-data access + untrusted-content ingestion + network exfil
- lowexfiltration combo
sensitive read and network capabilities split across this server's tools
analyzed commit d660639 · analyzer v18 · 2h ago
skills & prompt files 2
danger signals1
- suspicious endpointapi.telegram.orgparallelclaw-memex-mvp-d660639/bot/telegram.js:13
const API_BASE = 'https://api.telegram.org';
[](https://mcpobservatory.com/servers/github:parallelclaw/memex-mvp/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 parallelclaw.