github analyzed · update queued

AgentNDX

github

Search and discover MCP servers, A2A agents, and x402-enabled services. The agentic web's directory — add `https://agentndx.ai/mcp` to your MCP client to search 59+ servers by name, category, or capability. Pay $0.005 USDC per search via x402 micropayments — no API keys required.

maintainer
jl-3044
license
first seen
2026-07-03
last seen
2026-08-14
releases · 30d
0
short id
risk 59/100 · heuristic grade
C elevated
  • capability exposure inferred + 35
  • name impersonation inferred + 15
  • tool safety inferred + 9

inferred

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 1m ago · see ecosystem CVEs →

risk trajectory 1 movements
  • C · 44 C · 59
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

tool safety 3 findings · grade factor +9
  1. medium purpose mismatch get_server_details

    benign-looking name carries shell, secrets

  2. low exfiltration combo search_mcp_servers

    single tool reads + sends: net, secrets, db

  3. low purpose mismatch search_mcp_servers

    benign-looking name carries secrets

embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/smithery:jl-3044/agentndx/badge.svg)](https://mcpobservatory.com/servers/smithery:jl-3044/agentndx/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 jl-3044.