Agent Tools Mcp
@AgentTools-Cloud
Agent Tools Mcp について
Discover agent-callable resources by intent — x402 paid services, MCP servers and A2A agents — via the agent-tools.cloud directory. 9 tools: search/get/list_categories (x402), search_mcp_servers/get_mcp_server, search_agents/get_agent, search_all, stats.
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"agent-tools": {
"command": "uvx",
"args": [
"agent-tools-mcp"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Agent Tools Mcp?
Agent Tools Mcp powers agent-tools.cloud — an open directory of x402 paid services with a free MCP discovery endpoint. It provides a directory site, API endpoints for service search and submission, a streamable HTTP MCP discovery server, an A2A agent, and a standalone PyPI package (agent-tools-mcp). It is also listed on Smithery.
How to use Agent Tools Mcp?
Deploy via systemd with configuration from .env.example; required environment variables include UPSTREAM_BASE_URL, UPSTREAM_API_KEY, and AGENT_TOOLS_ASK_* settings for the LLM backend. Smoke-test with curl against endpoints like /healthz or /api/v1/ask. For MCP clients, install the agent-tools-mcp PyPI package or call the hosted /mcp-discovery/ endpoint.
Key features of Agent Tools Mcp
- Free directory of x402 paid services with faceted search
- MCP discovery server with streamable HTTP transport
- A2A JSON-RPC agent for directory search and safety scan
scan_mcp_safetytool to vet MCP servers for malware/prompt-injection- Intent-based service recommendations with LLM reranking
- Public API endpoints for search, stats, submission, and categories
Use cases of Agent Tools Mcp
- Discover and browse x402 monetized APIs and services
- Search for MCP servers by natural-language intent and filter by price, health, or category
- Safety-check an unknown MCP server before connecting
- Integrate directory search as an A2A skill into agents
- Submit new paid services to the directory for public listing
FAQ from Agent Tools Mcp
What is agent-tools.cloud?
It is an open directory of x402 paid services with a free MCP discovery endpoint, hosted at agent-tools.cloud.
Are the paid services (e.g., Qwen3.6 relay, vertical endpoints) still available?
No. They were retired after 30 days of zero external conversions. The server now serves only the directory site and the free MCP discovery server.
How do I use the MCP discovery server?
Install the standalone PyPI package agent-tools-mcp (Apache-2.0 licensed) or call the hosted endpoint at POST /mcp-discovery/ with a standard MCP initialize request.
What does scan_mcp_safety do?
It vets an MCP server by endpoint URL for malware, prompt-injection lures, and tool-poisoning coercion using deterministic static rules and an optional frontier-LLM second opinion — without executing code.
What runtime dependencies are required?
Python with uvicorn, an SQLite database path, and environment variables for upstream LLM API keys if using the ask, safety, or models features.
「AI とエージェント」の他のコンテンツ
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
Unreal Engine Generative AI Support Plugin
prajwalshettydevUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
コメント