The universal remote for AI: one MCP install gives agents 450+ callable endpoints across 60+ integrations, plus persistent cross-session memory. Works with Claude, ChatGPT, Cursor, and any MCP client.
Source not yet analyzed — this grade rests on attested signals (CVEs, supply-chain) only. It is a floor: reading the code could raise it, not lower it.
- capability exposureinferred+35
- inherited (deps)attested+15
- trust mitigatorsmixed−3
attestedinferredmixed
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.
inherited (deps) · grade factor +15
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed v0.3.99 · analyzer v18 · 9h ago
danger signals1
- suspicious endpointapi.telegram.orgpackage/dist/telegram-tool.js:4
const TELEGRAM_API_BASE = "https://api.telegram.org";
[](https://mcpobservatory.com/servers/npm:@unclick/mcp-server/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 malamutemayhem.