Agentic.ai Directory

io.github.u00dxk2由 GitHub 账号 u00dxk2 发布v2.0.0更新于 Oct 25, 2026

Independent directory of agentic AI tools — search, compare & recommend via MCP. Read-only.

发布方自己的服务:agentic.no

已验证Streamable HTTP可网页运行网页搜索与抓取知识与记忆

概览

AI 生成的概览

一个只读的远程 MCP 服务器,接入独立的智能体 AI 工具目录,让助手搜索、浏览、比较工具并获取推荐。

可以做什么
按关键词、自然语言或需求描述搜索并推荐工具,支持筛选和排序说明。读取单个工具的完整详情,包括功能、定价和智能体化评分。对两个工具做并排比较,返回结构化字段矩阵和选 A 或选 B 的结论。按分类、标签类型或最近新增浏览目录。查看某工具九维度智能体化评估的详细拆解。
适用场景
当用户想查找、筛选或比较智能体 AI 工具,或希望按描述的工作流程获得推荐,并且需要目录数据而非通用网页搜索时适用。
运行要求
位于 agentic.ai 的远程 streamable HTTP 端点;未声明软件包、环境变量或请求头,也未声明身份验证。需要能访问该端点的网络。
安装前请注意
只读目录访问;输入中未声明凭据、付费或写入操作。结果与评分来自第三方目录,排名和推荐应视为供应商提供的信息,而非中立评价。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Agentic.ai Directory,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.u00dxk2%2Fagentic-directory/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "agentic-ai-directory": {
      "type": "http",
      "url": "https://agentic.ai/mcp"
    }
  }
}

README

该仓库没有 README。

工具

10

search_listings

Search for agentic AI tools by keyword query with optional filters. Use this for keyword-based search. For natural language queries like 'something that automates email', use semantic_search instead. For browsing all tools in a category, use get_category instead.

输入参数limitquery必填cohortcategoryminScoremcpSupportopenSourceautonomyLeveldeploymentModel

get_listing

Get full details for one specific AI tool by its slug — includes features, pricing, agenticness scores, and structured attributes. Use this when you know the exact tool slug. To find a slug, use search_listings first. For comparing two tools, use compare_listings. Note: null on boolean fields means 'unknown', false means 'confirmed no'.

输入参数slug必填

compare_listings

Compare exactly two AI tools side-by-side. Returns structured field matrix and 'Choose A if... Choose B if...' verdict. Use this when a user wants to decide between two specific tools. For finding tools first, use search_listings or semantic_search.

输入参数slug1必填slug2必填

get_agenticness_details

Get the full agenticness evaluation breakdown: 9 dimensions (action capability, autonomy, planning, adaptation, state continuity, reliability, interoperability, safety, operator sovereignty) scored 0-4 each (max 36, Agenticness rubric v3.1) with evidence-based reasoning. Use this for deep analysis of one tool's AI agent capabilities. For a quick score, get_listing includes the overall score. For comparing scores, use compare_listings.

输入参数slug必填

list_categories

Get all categories with descriptions and listing counts. Use this to discover what categories exist before filtering. To get listings IN a category, use get_category with the slug. Categories are split into PEOPLE (individual use) and TEAMS (team/enterprise) cohorts.

无需输入参数。

get_category

Get all published listings in one specific category, sorted by agenticness score. Use this to browse a category. To see all categories first, use list_categories. To search across ALL categories, use search_listings or semantic_search.

输入参数slug必填

list_tags

Get all tags grouped by type (pricing, platform, capability, deployment, model, autonomy, use-case). Use this to discover available filter values. Tags can be used as filters in search_listings. This does NOT return listings — use search_listings or get_category for that.

无需输入参数。

list_recent

Get the most recently added AI tool listings, sorted by creation date. Use this to see what's new. For finding specific tools, use search_listings. For browsing by category, use get_category.

输入参数limit

recommend_tools

Get AI-powered tool recommendations for a specific need. This is the recommended starting point — describe what you're looking for in natural language and get curated, ranked results with explanations. Handles search, filtering, scoring, and ranking in one call. Use this instead of chaining search_listings + get_listing + compare_listings. Examples: - "best coding agent for a small startup on a budget" - "open source alternative to Cursor for VS Code" - "autonomous customer support agent with MCP support" - "self-hosted data analysis tool for enterprise"

输入参数question必填constraints

版本历史

1
  1. v2.0.0最新Sep 16, 2026

评分

已满足适用检查项的 75%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分

    请声明包含 README 的 GitHub 仓库,或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。

其他 Agentic 集成