# agent-tools (x402 + MCP + A2A directory)

> agent-tools (x402 + MCP + A2A directory) is a free MCP server for developer tools. Search and safety-check x402 APIs, MCP servers and A2A agents by intent. It can run locally on your machine or as a hosted remote server.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** API, CLI
- **Website:** https://agent-tools.cloud
- **Repository:** https://github.com/agenttools-cloud/agenttoolscollection
- **MCP Registry name:** cloud.agent-tools/agent-tools-mcp
- **Categories:** developer tools, web search and scraping
- **Listing updated:** 2026-11-14

## About

Scale is the reference point: the directory reports 95,842 indexed listings as of 2026-11-14, of which 74.4% answered the last probe and 43.6% are rated ready for an agent to call. It runs initialize and tools/list against remote MCP endpoints, reads x402 payment challenges for price and network, and fetches A2A agent cards, then grades each one.

The server exposes this to your agent. Tools include search by intent, ask_services for ranked recommendations, search_mcp_servers, search_a2a_agents, get_mcp_server, directory_stats, get_methodology and scan_mcp_safety, which checks an endpoint before you trust it. The README says no key is needed to search and a free key unlocks full statistics.

It installs from PyPI as agent-tools-mcp over stdio, or connects remotely over Streamable HTTP. Developers building agents that must pick or vet third-party tools are the audience.

## Features

- **Intent search:** Finds x402 services, MCP servers and A2A agents from a described need.
- **Ranked recommendations:** ask_services returns LLM-ranked picks grounded in directory candidates.
- **MCP safety scan:** scan_mcp_safety checks an MCP endpoint before an agent calls it.
- **Daily probe data:** Listings are probed daily for reachability, protocol handshake and grade.
- **Statistics and methodology:** Exposes aggregate stats and how grades are computed.
- **Two ways to connect:** PyPI stdio package or a remote Streamable HTTP endpoint.

## Good for

- Find an MCP server for a task by describing it
- Vet an MCP server before connecting an agent
- Compare pay-per-call x402 APIs by price
- Track how many listed servers pass a handshake

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http agent-tools-mcp https://agent-tools.cloud/mcp-discovery/
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://agent-tools.cloud/mcp-discovery/
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "agent-tools-mcp": {
      "url": "https://agent-tools.cloud/mcp-discovery/"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "agent-tools-mcp": {
      "type": "http",
      "url": "https://agent-tools.cloud/mcp-discovery/"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "agent-tools-mcp": {
      "serverUrl": "https://agent-tools.cloud/mcp-discovery/"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "agent-tools-mcp": {
      "type": "http",
      "url": "https://agent-tools.cloud/mcp-discovery/"
    }
  }
}
```

## Tools

- `search`: Find x402 / MCP services matching an intent or filter set. Two usage modes (agents pick whichever fits): A. Natural-language: `search(intent="fetch tweets for @user")` B. Pure browse: `search(has_mcp=True, category="defi", top_k=10)` At least one of `intent`, `category`, `chain`, `has_mcp`, `min_confidence` must be supplied — otherwise the call is rejected (we won't dump 2300+ rows). Results are r
- `ask_services`: Ask for the best x402/MCP services for an agent intent. This is the high-level discovery tool: it retrieves candidates from the directory, asks the configured backend LLM to rank only those candidates, and returns service cards for the selected recommendations. If the LLM is unavailable, it falls back to the directory ranker. Args: intent: Natural-language job the agent wants to accomplish. top_k:
- `get`: Get full details + ready-to-paste call template for a service. Returns the service card with payment, call, quality, resource samples, and ready-to-use MCP/x402 call hints. Use this after `search` or `ask_services` before paying/calling an external service. Args: slug: Service slug as returned by `search` items.
- `list_categories`: List all available service categories in the directory.
- `stats`: High-level stats about the directory: x402 total, healthy count and chains, plus `snapshot`, the daily digest across x402, MCP and A2A (see directory_stats).
- `get_methodology`: How every score and statistic on agent-tools.cloud is computed. Returns the quality-score components and grade bands per protocol, the nine readiness criteria with weights, payment-evidence grades, the probing schedule and the definitions behind the daily statistics.
- `list_articles`: List published Blog articles, newest first (metadata only). Args: query: Optional words to match in title, summary or body. tag: Optional tag to filter by. page: Page number, 20 articles per page. Use get_article(slug) for the full Markdown body.
- `get_article`: Read one published Blog article: metadata plus the full Markdown body. Args: slug: The article slug, as returned by list_articles.
- `directory_stats`: Daily statistics on the agent-tool ecosystem as seen by our probes. Args: view: "all", "mcp", "x402" or "a2a" to scope the figures to one protocol. topic: Optional topic word (e.g. "payment", "weather") to get that topic instead: supply per protocol, readiness, best listings, searches. month: Optional "YYYY-MM" to get that monthly report instead. api_key: Optional account key (free from create_api
- `search_mcp_servers`: Find MCP servers in the directory. Searches the standalone MCP directory (official MCP Registry, Smithery, Agenstry and other crawled sources) unioned with x402 services that also expose an MCP endpoint. Returns normalised entries with a ready-to-use streamable-http `call_hint.mcp.url`. Args: intent: Natural-language description of the tool/capability needed. top_k: Max servers to return (1-20). c
- `get_mcp_server`: Get the full card for one MCP server by slug. Args: slug: MCP server slug as returned by `search_mcp_servers` items.
- `search_a2a_agents`: Find A2A agents you can delegate a task to. Args: intent: Natural-language description of the task to delegate. top_k: Max agents to return (1-20). x402_only: When true, only return agents that advertise x402 payment.
- `search_resources`: Unified search across x402 services, MCP servers and A2A agents. Args: intent: Natural-language query. protocol: Optional filter: "x402", "mcp" or "a2a". top_k: Max resources to return (1-50).
- `register`: Self-register an x402 / MCP service in the agent-tools directory. Service owners and agents may submit new services here. Submissions are auto-reviewed instantly by x402 verification (no human gate): if the URL proves x402 payment support it is listed immediately and shows up in `search`; otherwise it is rejected or retried automatically. Listing is FREE. Dedup: if a service with the same canonica
- `scan_mcp_safety`: Check an MCP server for malware / prompt-injection lures by its endpoint URL. Give the server's streamable-http endpoint URL. Two paths: * **Already in the agent-tools directory** → returns our LATEST stored rule verdict. Every indexed server is re-scanned hourly, so you get a consistent, continuously-refreshed answer without re-probing. * **Not yet indexed** → we probe the endpoint live, statical
- `claim_service_url`: Issue a fresh ownership token for one exact public HTTPS URL. Authenticate in the MCP Authorization: Bearer header. Publishing and verifying the token is required before editing; URL input alone grants no rights. Args: url: Complete public HTTPS service URL, including its query when present. method: Optional proof method; otherwise inferred from the complete URL.
- `verify_service_url`: Verify public ownership proof for your own exact service URL claim. This reads public proof only. It never calls business tools, requests private service credentials, or grants whole-platform permissions. Args: claim_id: Claim id returned by claim_service_url. token: The issued token after publishing it in the instructed location.
- `get_owned_listing`: Read editable metadata for a listing covered by your verified claim. Args: kind: Listing type: x402, mcp, or a2a. slug: Slug from the verified claim's listings or directory search.
- `edit_owned_listing`: Edit only metadata covered by your verified claim, with the public audit trail. An endpoint change requires verified control of the exact destination or its whole host and clears measurements tied to the old primary endpoint. Args: kind: Listing type: x402, mcp, or a2a. slug: Slug of the listing you are authorized to edit. fields: Editable fields to change; measured fields are rejected.
- `create_api_key`: Create a free account API key. No sign-up, email or existing key needed. The key is returned once and cannot be recovered. Store it in your secret store; do not print it back to the user or write it to logs. Send it as `Authorization: Bearer <key>` (or the `api_key` argument where offered) to get complete `directory_stats` lists, run paid verifications and claim your own listings. The claim and li
- `prepare_paid_verification`: Quote a sponsored paid verification of an x402 service. You pay the service once from your own wallet (Base USDC, <= $1; funds go to its payTo). Sign the returned `typed_data` (EIP-712), then call `execute_paid_verification` before `valid_before`. We never sign or hold funds. Auth: API key from POST https://agent-tools.cloud/api/v1/keys, as the `Authorization: Bearer` header or `api_key`. Args: sl
- `execute_paid_verification`: Send the signed payment to the service once and score the result. Aborts without paying if price or recipient changed. Never retried; a timeout returns `indeterminate`. status: succeeded | delivery_failed | payment_rejected | indeterminate. Args: id: `id` returned by `prepare_paid_verification`. signature: 0x EIP-712 signature of its `typed_data` by the payer. api_key: Optional if the Authorizatio
- `get_paid_verification`: Read one of your own paid verifications. Args: id: Verification id. api_key: Optional if the Authorization header is sent.

## FAQ

### Do I need an API key?

Not to search. The site says a free key unlocks the full statistics.

### How is it installed?

As the PyPI package agent-tools-mcp (version 0.5.2 in the registry) over stdio, or via the remote endpoint.

### What protocols does the index cover?

x402 paid APIs, MCP servers and A2A agents.

### Is the directory data open?

The README says daily statistics are published as JSON and CSV under CC BY 4.0.

### Is agent-tools (x402 + MCP + A2A directory) free?

Yes. agent-tools (x402 + MCP + A2A directory) is free to use.

### How do I add agent-tools (x402 + MCP + A2A directory) to Claude Code?

Run this command in your terminal: claude mcp add --transport http agent-tools-mcp https://agent-tools.cloud/mcp-discovery/

### What are the best alternatives to agent-tools (x402 + MCP + A2A directory)?

The closest alternatives to agent-tools (x402 + MCP + A2A directory) are REA, Scrapling MCP Server, Codebase Memory, GitHub and Serena MCP: the IDE for your agent.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/agent-tools-x402-mcp-a2a-directory-2
