Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Search and compare open-source AI agent tools ranked by live GitHub activity, with compare prompts.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
适用于网页版、桌面版和手机版 Claude:
https://agentoolrank.com/api/mcp在终端中运行这条命令
claude mcp add --transport http agent-tools https://agentoolrank.com/api/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"agent-tools": {
"url": "https://agentoolrank.com/api/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"agent-tools": {
"type": "http",
"url": "https://agentoolrank.com/api/mcp"
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
ChatGPT 只能连接互联网上的服务器:
https://agentoolrank.com/api/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 agentoolrank.com 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.1.1)于31天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Search and compare open-source AI agent tools from your AI assistant, ranked by live GitHub activity.
AgentoolRank tracks hundreds of open-source AI agent tools (frameworks, coding agents, memory, RAG, evals, MCP servers) and ranks them by GitHub activity: stars, star pace, commits, releases and package downloads, refreshed daily. This repository documents how to connect to its hosted MCP server and JSON API. The server runs on agentoolrank.com; there is nothing to install or self-host.
https://agentoolrank.com/api/mcp (Streamable HTTP, no auth required)com.agentoolrank/agent-toolsAuthorization: Bearer to identify your agent.| Tool | What it does |
|---|---|
search_tools(query, limit?) | Find tools for a job, ranked by relevance then GitHub activity. |
get_tool(slug) | Stars, 30-day star growth, capabilities, limitations and who it is best for. |
get_alternatives(slug) | Open-source alternatives to a tool, with their GitHub stats. |
submit_tool(url, name, tagline, email, …) | List a tool. The response shows every pricing option up front, including the free one. |
get_submission_status(submission_id, status_token) | Review status of a submission. |
recommend_directories(product_type) | Launch directories our own products went through, with free-tier conditions and the steps only a person can do. The top 5 for each product type are free. |
next_directory(key, product_type?) | Submit Kit key (9): hands your agent the next directory that fits the product, one at a time (up to 50, at most 3 unreported). |
report_result(key, domain, status, listing_url?) | Submit Kit key: report what happened at a directory. Reports are leads; listing rates count only listings our own daily check verifies. |
my_progress(key) | Submit Kit key: every directory handed out so far and its reported status (also at agentoolrank.com/submit-kit/progress). |
Ready-made prompts your MCP client can offer (prompts/list, prompts/get):
| Prompt | Arguments | What it does |
|---|---|---|
compare_tools | tool_a, tool_b | Compares two tools side by side: GitHub stars, 30-day star growth, last release, downloads, best for, limitations |
find_alternatives | tool | Lists open-source alternatives to a tool, ranked by live GitHub activity |
launch_plan | product_type (ai_tool, mcp_server, dev_tool, saas, other), optional product_url | Plans where to list a new product: which launch directories fit it and which to skip |
| URI | Content |
|---|---|
agentoolrank://about | How the ranking works and what this server offers (Markdown) |
agentoolrank://top-tools | The current top 20 open-source AI agent tools by GitHub activity, live (Markdown table) |
claude mcp add --transport http agentoolrank https://agentoolrank.com/api/mcp
Add to ~/.cursor/mcp.json (or .cursor/mcp.json in a project). See examples/cursor-mcp.json:
{
"mcpServers": { "agentoolrank": { "url": "https://agentoolrank.com/api/mcp" } } }
Add it under Settings → Connectors as a custom connector with the URL above. Or use the mcp-remote bridge in claude_desktop_config.json. See examples/claude_desktop_config.json.
Add to ~/.codex/config.toml. See examples/codex-config.toml.
The same data is also available without MCP. See examples/curl.sh.
GET https://agentoolrank.com/api/v1/tools?q=rag&limit=10
GET https://agentoolrank.com/api/v1/tools/{slug} POST https://agentoolrank.com/api/v1/submissions
AgentoolRank is run by TENSO LLC. Questions or corrections: hello@agentoolrank.com. Privacy · Terms.
The contents of this repository (documentation and configuration examples) are MIT licensed. The AgentoolRank website, data and service are not part of this repository.