agent-tools-mcp
Discover agent-callable resources from your agent.
Community: Submitted by a user or imported; check the owner before granting accessOnlineNo sign-inGlobalFreeRead-only
What it can do
- Search: Find x402 paid services matching a natural-language intent. Results are ranked by: health → has-quality-signal → confidence → 30-day transaction volume → last-updated. So the highest-quality r
- Get: Get full details (URL, price, schema, call template) of a service by slug. Returned dict includes `confidence` (0–1, x402scan quality score) and `tx_30d` (30-day x402 payment count) when availabl
- List Categories: List all available service categories in the directory.
What data it sees
Do you need an account
No: the server works without sign-in
Discover agent-callable resources from your agent. agent-tools-mcp is a discovery layer over the agent-tools.cloud directory, which indexes three kinds of resources and exposes them as MCP tools:
- x402 services — pay-per-call HTTP APIs (USDC on Base).
search/get/list_categories. - MCP servers — external tools & context via MCP.
search_mcp_servers/get_mcp_server. - A2A agents — delegate a task to a peer agent.
search_agents/get_agent. - Unified —
search_allsearches all three at once;statsreports live directory size & health.
A2A tells agents who can do the job, x402 lets them pay for it, MCP gives them the tools to do it. Search by intent, filter by price / chain, read the full call template, then call.
This is a discovery layer, not a facilitator — your agent keeps full custody of payment; we just help it find the right resource.
- Repo: https://github.com/AgentTools-Cloud/AgentToolsCollection
- PyPI:
pip install agent-tools-mcp - Remote (free, streamable-http): https://agent-tools.cloud/mcp-discovery/
- License: Apache-2.0
Server tool list (4)
Raw names from tools/list. Only developers need these.
| search | Find x402 paid services matching a natural-language intent. Results are ranked by: health → has-quality-signal → confidence → 30-day transaction volume → last-updated. So the highest-quality real-traffic services appear first. Each item in the response includes (when available): - confidence : 0.0–1.0 quality score from x402scan (higher = more reliable / validated by the explorer). - tx_30d : x402 payments observed in the last 30 days (proxy for real usage; 0 or null for unproven services). Agents should prefer items with non-null confidence and tx_30d > 0 unless the user explicitly wants experimental endpoints. Args: intent: What the agent wants to do (English or Chinese), e.g. "fetch user tweets", "check on-chain whale activity". top_k: Max number of services (default 5, max 25). max_price_usd: Hard upper bound on per-call price in USD. category: Optional category filter (see `list_categories`). chain: Optional chain filter ("base", "polygon", "arbitrum", ...). min_confidence: Optional minimum confidence threshold (0.0–1.0). E.g. 0.8 keeps only services x402scan rates as high-quality. |
| get | Get full details (URL, price, schema, call template) of a service by slug. Returned dict includes `confidence` (0–1, x402scan quality score) and `tx_30d` (30-day x402 payment count) when available — use these to judge whether a service is production-ready before calling it. |
| list_categories | List all available service categories in the directory. |
| stats | High-level stats about the directory: total services, healthy count, sources. |