Raptr Agent Finder

com.airaptr由 airaptr.com 发布官方发布者v1.0.0更新于 Oct 24, 2026

Find a free, ready-made AI agent for a task in the open agent registry (RAR).

发布方自己的服务:Dogg World Check

已验证Streamable HTTP可网页运行开发者工具AI 与机器学习

概览

AI 生成的概览

一个远程 MCP 服务器,让助手搜索公开的现成单文件 AI 智能体注册表、读取其源码,并在对话中运行其中一个。

可以做什么
在开放智能体注册表中搜索已完成某任务的现成智能体,避免从零构建,并在使用前判断是否合适。按名称获取注册表中某个智能体的完整源码,以便阅读或改写。获取一段简短的 Python 运行器,在对话中用用户粘贴或上传的数据试用某个智能体。获取可选的说明,了解如何用免费的 Brainstem 把智能体长期运行在用户自己的电脑上。在用户同意后,转交这些工具无法完成的需求。
适用场景
适合用户询问是否已有现成的 AI 工具完成某项任务、想要现成自动化而非自行开发,或希望在正式采用前查看并在自己的数据上试用注册表中的智能体时使用。
运行要求
远程 streamable HTTP 端点;未声明需要安装软件包、账号、API 密钥或环境变量。在对话中试用智能体需要助手具备可用的 Python 工具。
安装前请注意
注册表中的智能体源码属于第三方代码,运行或改写前应先审阅。运行器会在用户提供的数据上执行智能体,应避免敏感内容。请求工具会记录用户同意发送的请求文本,不含姓名和联系方式,调用前应先确认。README 提到一个付费的 x402 端点用于另一项拒绝诊断功能,该功能不在所列工具中。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Raptr Agent Finder,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/com.airaptr%2Fraptr-agent-finder/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": {
    "raptr-agent-finder": {
      "type": "http",
      "url": "https://api.airaptr.com/finder/mcp"
    }
  }
}

README

Raptr Agent Builder (ChatGPT app)

A ChatGPT app that turns an idea or a meeting transcript into a working single-file agent. ChatGPT's own model writes the agent; this MCP server supplies the template, checks the result, searches the public open agent registry (RAR), and explains how to run the agent in the free Brainstem.

It sits on top of the ecosystem and never changes the Brainstem: it reads the public registry and points at the public installer.

  • MCP endpoint: https://airaptr-api.azurewebsites.net/mcp (streamable HTTP, stateless, JSON responses)
  • Site, privacy, terms: https://airaptr.github.io/

Tools

ToolWhat it does
get_agent_templateThe official template and its rules
check_agentChecks a finished agent file against the rules
find_agentsSearches the registry
get_agent_codeReturns one registry agent's source
use_agent_hereRunner so ChatGPT runs the agent in the chat on the user's data
how_to_run_agentOptional: keep it on your computer (Mac, Windows, Linux)
rejection_rescue_previewFree: explains the guideline sections an Apple App Review rejection cites

Store: GET /store.json is the catalog for agents. Rejection Rescue: free preview at POST /rescue/preview, the full diagnosis and reply draft at POST /x402/rescue (x402, X402_PRICE_RESCUE, default $0.50, testnet by default). Tests: node --test test/*.test.mjs.

Develop

bash
node build_template.mjs ../RAR/template_agent.py   # refresh the embedded templatenpx wrangler dev                                   # local server on :8787node test/check_real_agents.mjs ../RAR             # checker vs. the template and every registry agenttest/mcp_smoke.sh http://localhost:8787            # drive the MCP endpointnpx wrangler deploy                                # Cloudflare hostazure/deploy.sh                                    # or Azure Functions

Listing copy for the ChatGPT app directory is in SUBMISSION.md.

来源:README.md,提交 f110430

工具

5

find_agents

Find existing agents

Searches the open agent registry (about 1,700 single-file agents) for agents that already do what the user wants, for example when they ask 'is there an AI tool for...' or want a ready-made automation instead of building one. Use it before building from scratch, or when the user asks whether an agent exists for a task.

输入参数limitquery必填

get_agent_code

Get an agent's code

Returns the full source of one agent from the registry, by its name (e.g. @bill/neuron_agent), so it can be read or adapted.

输入参数name必填

use_agent_here

Use the agent in this chat

Use this right after an agent passes check_agent, or whenever the user wants to try an agent. Returns a short Python runner so you can run the agent in this chat with your own Python tool on the user's own data (pasted text, an uploaded spreadsheet, a list). Nothing to install. If Python is unavailable, apply the agent's logic yourself by reading its code. Ask the user for their real data, run the agent, and show the result in plain words.

输入参数filename

how_to_run_agent

Keep an agent running on your computer

Optional, for later: how to keep an agent running on the user's own computer with the free Brainstem. Only offer this after the user has used the agent in the chat and wants to keep it.

输入参数osfilename

request_service

Ask us to build something

Use when the person wants something none of these tools can do and says yes to passing the request on. Records only the request text they agree to send (no name or contact). Ask before calling it.

输入参数request必填

版本历史

1
  1. v1.0.0最新Oct 16, 2026

评分

已满足适用检查项的 90%

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
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。

其他 Airaptr 集成