agent-tools (x402 + MCP + A2A directory)
by agent-tools.cloud MCP server in Cloud & infrastructure, indexed and not reviewed
HostedLocalvendor's ownhosted, answers
Not reviewed
No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.
Discover x402 services, MCP servers and A2A agents by intent — agent-tools.cloud directory.
Facts
- MCP registry
cloud.agent-tools/agent-tools-mcp· 0.5.2- Endpoint
https://agent-tools.cloud/mcp-discovery/- Packages
pypiagent-tools-mcp stdio- Website
- agent-tools.cloud
- PyPI / week
- 75
- GitHub stars
- 1
- Endpoint answered
- with a tool list, 8 Nov 2026
- Registry entry
- updated 14 Nov 2026
From the official MCP registry, the package registries and our own checks. JSON · Markdown
Why it's listed
- It's published in the registry under agent-tools.cloud, a namespace the registry only gives to whoever proves they control that domain.
- Its hosted endpoint answered our tools/list on 8 Nov 2026 with a tool list.
Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.
Tools it lists 23 · about 8,132 tokens of context · checked 2 hours ago
| Tool | What it does | Hint |
|---|---|---|
search | withheld | read-only |
ask_services | withheld | read-only |
get | withheld | read-only |
list_categories | withheld | read-only |
stats | withheld | read-only |
get_methodology | withheld | read-only |
list_articles | withheld | read-only |
get_article | withheld | read-only |
directory_stats | withheld | read-only |
search_mcp_servers | withheld | read-only |
get_mcp_server | withheld | read-only |
search_a2a_agents | withheld | read-only |
search_resources | withheld | read-only |
register | withheld | writes |
scan_mcp_safety | withheld | writes |
claim_service_url | withheld | writes |
verify_service_url | withheld | writes |
get_owned_listing | withheld | read-only |
edit_owned_listing | withheld | writes |
create_api_key | withheld | writes |
prepare_paid_verification | withheld | writes |
execute_paid_verification | withheld | writes |
get_paid_verification | withheld | read-only |
What https://agent-tools.cloud/mcp-discovery/ answered to tools/list, asked without credentials over MCP 2025-11-25. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.
How its tools read to an agent 2 errors · 4 warnings · 1 note
Its tool definitions contain text aimed at the model (TC19), which is how tool poisoning is written, so this site doesn't repeat them. An agent shouldn't connect to it without its user's say-so.
- errorTC19scan_mcp_safetythe definition tells the model to ignore its instructions
- errorTC19scan_mcp_safetythe definition wraps text in tags meant for the model
- warnTC07scan_mcp_safetythe description is about 794 tokens
- warnTC07searchthe description is about 509 tokens
- warnTC13edit_owned_listingfields (object with no properties)
- warnTC20scan_mcp_safetythe description steers the model
- noteTC29serverabout 736 tokens (9% of the definitions) are titles that repeat property or function names
The checks from /check and anchor check, run each day on the list above: about 8,132 tokens of definitions. Not part of the score yet. Check your own server.