agent-tools-mcp

Discover agent-callable resources from your agent.

CommunityOnlineNo 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_all searches all three at once; stats reports 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.

How to connect

How to connect agent-tools-mcp to Claude

The server address to paste into Claude settings:

https://agent-tools-mcp--kangletian.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect agent-tools-mcp to ChatGPT

The server address to paste into ChatGPT settings:

https://agent-tools-mcp--kangletian.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect agent-tools-mcp to Cursor

The server address to paste into Cursor settings:

https://agent-tools-mcp--kangletian.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (4)

Raw names from tools/list. Only developers need these.

searchFind 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.
getGet 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_categoriesList all available service categories in the directory.
statsHigh-level stats about the directory: total services, healthy count, sources.