Agent Nexus

Registry of 180+ continuously tested APIs, MCP servers and CLIs that AI agents can call, with endpoint, auth, limits and reliability score.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "Agent Nexus": {
      "url": "https://agentnexus--ceo-2z03.run.tools"
    }
  }
}

工具	说明
discover_capabilities	Match a natural-language need (e.g. 'send a transactional email', 'query Postgres') to the interfaces that can do it, ranked by capability match and verified reliability. Returns everything needed to call them: endpoint, auth mode, auth parameters, formats, rate limit and cost. Always returns a payload: when nothing matches, `coverage` is 'none', `uncovered` is true and the entries returned are reliable starting points, not matches.
search_registry	Search the Agent Nexus registry of approved APIs, MCP servers and CLIs by keyword and optional category.
get_entry	Fetch one approved Agent Nexus registry entry by slug, including its endpoint, auth method and last health probe.
list_categories	List the three interface layers Agent Nexus indexes (APIs, MCPs, CLIs) with the number of approved entries in each.
list_entries	List every approved entry in the Agent Nexus registry, page by page. Returns up to 50 entries per page, ordered by slug, with the total count so you can page through the whole catalogue. Use search_registry for keyword lookup instead.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。