Home / MCP registry index / io.github.traveljamboree/agentsec-mcp
AgentSec MCP
io.github.traveljamboree/agentsec-mcp in the official MCP registry.
Endpoint https://agentsec-mcp.agentsec-mcp.workers.dev/mcp.
The registry describes it as: Security intelligence via x402 on Base. CVE lookup, IP reputation, secret scanning.
We read its 3 tools on 2026-10-22. Nothing in them matched our tool-poisoning rules.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
cve_lookup reputation_check secret_scan
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-traveljamboree-agentsec-mcp)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.
Related
Crypto and Web3 MCP servers · Security MCP servers
| The Stall ai.intuitek.the-stall/the-stall | 200 tools, nothing matched 2026-10-22 |
| SAP MCP Server ai.oobeprotocol.sap.mcp/sap-mcp | 200 tools, nothing matched 2026-10-22 |
| uk.minia2a/minia2a-mcp-remote uk.minia2a/minia2a-mcp-remote | 200 tools, nothing matched 2026-10-21 |
| AI 代理人任務中樞 dev.workers.panda198271.agent-hub-tw/agent-hub | 174 tools, nothing matched 2026-10-22 |
| ai.firmbrain/x402-services ai.firmbrain/x402-services | 159 tools, nothing matched 2026-10-21 |
| Geode com.geodeapps.mcp/geode | 138 tools, nothing matched 2026-10-22 |