Skip to main content

agent-tools-mcp

smithery badge MCP PyPI License

Discover agent-callable resources from any MCP-compatible agent (Claude, Cursor, Cline, Continue, …).

Backed by agent-tools.cloud, an open directory that indexes three kinds of agent-callable resources:

Resource What it solves Typical object
x402 service agent pays per call for an HTTP API /.well-known/x402, 402 endpoint, payTo
MCP server agent gains external tools & context Streamable-HTTP / stdio MCP servers
A2A agent agent delegates a task to another agent /.well-known/agent-card.json, A2A JSON-RPC

A2A tells agents who can do the job. x402 lets them pay for it. MCP gives them the tools to do it.

This is a discovery layer, not a facilitator — your agent keeps full custody of payment. The tools never auto-pay; they only find resources and return call templates. Call the stats tool for live counts across all three protocols.

Also listed on Smithery for one-click hosted install.

Tools

Tool What it does
search(intent, top_k, max_price_usd, category) Natural-language search across x402 paid services
get(slug) Full details (URL, price, call template) of an x402 service
list_categories() Browse x402 categories
search_mcp_servers(intent, top_k, chain) Find MCP servers by intent
get_mcp_server(slug) Full MCP server record (endpoint, transport, capabilities)
search_agents(intent, top_k, x402_only) Find A2A agents to delegate a task to
get_agent(slug) Full A2A agent card (endpoint, skills, auth, x402 info)
search_all(intent, protocol, top_k) Unified search across all three; each result tagged with protocol
stats() Directory size & health across x402 / MCP / A2A
ask(question, top_k, max_price_usd, chain, category) Plain-language recommendation: a written answer plus the ranked x402/MCP services behind it
recommend(intent, top_k, max_price_usd, chain) Scored x402 shortlist with price_hint / pay_hint (discovery only, never pays)

Typical flow: ask ask for a recommendation, start with search_all if you don't know which resource type fits, or go straight to the protocol-specific search (search / search_mcp_servers / search_agents), then call the matching get* tool for the full call template.

What agents get back

search() / get() return a normalised service record: endpoint URL, method, price range, settlement network/asset, payTo, health and quality signals, plus whatever call metadata the provider publishes (x402 v2 extensions.bazaar input/output schema, OpenAPI, or an MCP tools/list). Entries come from the provider's own /.well-known/x402, x402scan, x402.org, the MCP Registry, PulseMCP and public A2A agent-cards; agent-tools.cloud re-probes them and adds health, latency and on-chain activity, but does not proxy or host the paid endpoints.

Retired listings return {"error": "retired", "status": 410} instead of raising.

Quick Start

Claude Code CLI

claude mcp add agent-tools -- uvx agent-tools-mcp@latest

Claude Desktop / Cursor / Cline

Add to your MCP config (~/.config/Claude/claude_desktop_config.json, ~/.cursor/mcp.json, …):

{
  "mcpServers": {
    "agent-tools": {
      "command": "uvx",
      "args": ["agent-tools-mcp"]
    }
  }
}

Remote (no install)

Most clients also accept a url-based remote MCP server (Streamable HTTP; the client must send Accept: application/json, text/event-stream):

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

From source

pip install agent-tools-mcp        # or `uv tool install agent-tools-mcp`
agent-tools-mcp                    # stdio server, ready for an MCP client

Environment Variables

Var Default Purpose
AGENT_TOOLS_API_BASE https://agent-tools.cloud Point at a different deployment (e.g. self-hosted)
AGENT_TOOLS_LOG_LEVEL INFO Server log level (stderr only)
AGENT_TOOLS_HTTP_LOG_LEVEL WARNING httpx/httpcore log level

Debugging

# Probe with the official MCP Inspector
npx -y @modelcontextprotocol/inspector uvx agent-tools-mcp

# Or raw JSON-RPC
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' | uvx agent-tools-mcp

License

Apache-2.0. See LICENSE.

Metadata

Release files for agent-tools-mcp 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for agent-tools-mcp 0.3.0
File Size Uploaded Provenance Actions
agent_tools_mcp-0.3.0.tar.gz 10.2 kB Without provenance Details for agent_tools_mcp-0.3.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for agent-tools-mcp 0.3.0
File Interpreter ABI Platform Actions
agent_tools_mcp-0.3.0-py3-none-any.whl Python 3 none any Details for agent_tools_mcp-0.3.0-py3-none-any.whl

Total release size: 19.7 kB

Release files / agent_tools_mcp-0.3.0.tar.gz

Download URL agent_tools_mcp-0.3.0.tar.gz
Size 10.2 kB
Tags Source
SHA-256 checksum
How to use checksums
1b5fdd2def844b4443066e1caa696d33665d9ee30052b63bee8436034bb5e85a
BLAKE2b-256 checksum
How to use checksums
e027ef04e0c1c24aaf94a5b523311e94aa8983d63369187ee158a0231f8f76d5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.3

Release files / agent_tools_mcp-0.3.0-py3-none-any.whl

Download URL agent_tools_mcp-0.3.0-py3-none-any.whl
Size 9.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
553e5fa958a07b9e660ff6ab0da75769f018ee318ce076e7e19aeb19585d2aa5
BLAKE2b-256 checksum
How to use checksums
0bad831479322f12e7d8483a7bc7cde291352a7922c5f3760a69b6a8dc12a55c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.3

Security for agent-tools-mcp 0.3.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page