MCP AI Agent Server
UnverifiedREPOsingularitybridge/mcp-ai-agent-server
D
Catalogue entry updated 3 days ago
Auth postureNot probedno remote endpoint probed yet
Tools51 Destructive · 1 Execute · 3 Read
Worst categoryDestructivegrade tracks the peak, not the average
Capability mix
Destructive 1Execute 1Read 3
What it can reach
Ingests untrusted inputTouches secretsReaches networkRuns codeTouches filesChanges permissionsSends external commsPersistsDeletes dataMoves money
Change history
No changes recorded since first scan. Watched servers surface a diff within the hour.
Recommended policy
clear_sessiondeny
send_messagerequire approval
Read-only toolsallow
Full policy breakdown with enforcement rules →