agent-tools (x402 + MCP + A2A directory) D
io.github.AgentTools-Cloud/agent-tools-mcp · v0.5.2 · score 49/100 · checked 2026-11-22
Discover x402 services, MCP servers and A2A agents by intent — agent-tools.cloud directory.
Source: https://github.com/AgentTools-Cloud/AgentToolsCollection
Findings
| Severity | Rule | Detail |
|---|---|---|
| low | AG005 | Remote endpoint lists 23 tool(s) to anyone, no credentials needed. |
| critical | AG101 | tool 'scan_mcp_safety': description contains instruction-like text aimed at the model ('ignore previous instructions'). Possible tool poisoning. |
| medium | AG102 | 1 tool(s) can execute commands or delete data (execute_paid_verification). Require confirmation before the agent calls them. |
What was checked
- https://agent-tools.cloud/mcp-discovery/: answers without auth
- pypi: agent-tools-mcp@0.5.2 (static checks only; code not executed)
Public tools: search, ask_services, get, list_categories, stats, get_methodology, list_articles, get_article, directory_stats, search_mcp_servers, get_mcp_server, search_a2a_agents, search_resources, register, scan_mcp_safety, claim_service_url, verify_service_url, get_owned_listing, edit_owned_listing, create_api_key, prepare_paid_verification, execute_paid_verification, get_paid_verification
Maintainer? Fix, then add the badge
Grades refresh daily.
[](https://agentguard-pi.vercel.app/s/io-github-agenttools-cloud-agent-tools-mcp-b830b11d)
agentguard: static and read-only checks. A grade is not a guarantee of safety. Index · Scanner