8123

Exa Search

Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with ...

Exa Fetch

Read a webpage's full content as clean markdown. Use after web_search_exa when highlights are insufficient or to read any URL. Best for: Extracting full content from known URLs. Batch multiple URLs in one call. Returns: Clean text content and metadata from the page(s).

Tavily Search

Search the web for current information on any topic. Use for news, facts, or data beyond your knowledge cutoff. Returns snippets and source URLs.

Tavily Extract

Extract content from URLs. Returns raw page content in markdown or text format.

Tavily Crawl

Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.

Tavily Map

Map a website's structure. Returns a list of URLs found starting from the base URL.

Tavily Research

Perform comprehensive research on a given topic or question. Use this tool when you need to gather information from multiple sources, including web pages, documents, and other resources, to answer a question or complete a task. Returns a detailed response based on the research findings. Rate limit: 20 requests per minute.

Resolve Library Id

Resolves a package/product name to a Context7-compatible library ID and returns matching libraries. You MUST call this function before 'Query Documentation' tool to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. Each result includes: - Library ID: Context7-compatible identifier (format: /org/project) - Name: Library or package name - Description: Short summary - Code Snippets...

Query Docs

Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework. You must call 'Resolve Context7 Library ID' tool first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query. Do not call this tool more than 3 times per question.

Firecrawl Scrape

抓取单个网页内容，支持 Markdown / HTML / 截图等多种输出。注意：此工具返回的 scrapeId 不用于 interact；交互会话请使用 firecrawl_new_session / firecrawl_continue。

Firecrawl Map

Map a website to discover all indexed URLs on the site.

Firecrawl Search

Search the web and optionally extract content from search results. Returns richer results than standard search with full-page content extraction and domain filtering.

Firecrawl Crawl

Crawl a website starting from a base URL, discovering and extracting content from multiple pages.

Firecrawl Extract

Extract structured information from web pages using LLM capabilities. Provide URLs and a prompt describing what to extract.

Firecrawl Oneshot

纯 keyless 一次性浏览器交互：多区域并发竞速（默认 3）+ 串行兜底（最多 5），首个成功即返回并关闭会话。首步 prompt/code 可能执行多次，勿用于不可重复写操作。

Firecrawl New Session

新建纯 keyless 可续步浏览器会话：首步多区域并发竞速（默认 3）+ 串行兜底（最多 5），返回首个有效 sessionId，后台清理输家。首步 prompt/code 可能执行多次，不要用于提交表单、发送消息等不可重复写操作。后续只用 firecrawl_continue 传 sessionId。

Firecrawl Continue

续步浏览器交互：固定原 Session DO 与出口身份。默认仅对明确未执行的 job-not-found/短暂429同身份重试，避免重复执行有副作用的操作。

Firecrawl Interact

纯 keyless 实时浏览器交互。首步只传 {url, prompt/code, autoStop:false}；续步推荐使用 firecrawl_continue，只传 sessionId + prompt/code；结束使用 firecrawl_interact_stop。scrapeId 由 Session DO 内部维护。已有资源不会切 API key、代理或节点；若返回 affinity_lost/flow_restart_required，必须丢弃旧 sessionId 从首步重开。

Firecrawl Interact Stop

关闭浏览器交互会话并释放资源。只需要 sessionId；scrapeId 由 Session DO 内部维护。

Github Search Code

Search code across public GitHub repositories using GitHub's code search API. Returns matching files with repository name, file path, and clickable URLs. Supports qualifiers: language:NAME, repo:OWNER/NAME, path:DIR, extension:EXT, org:NAME, user:NAME, filename:PATTERN, size:N.

Fetch Markdown

Fetch any web page as clean Markdown via Jina Reader API. Returns title, source URL, and main content with links preserved. Free, no API key needed. Supports optional JSON output format and caching control.

Fetch Html

抓取任意网页的原始 HTML 源码。

Web Search

网页搜索。同时查询 DuckDuckGo、Bing、Google 三个搜索引擎，合并去重后返回标题、URL、摘要。覆盖面比单一引擎更广。

Web Search Full

网页搜索并获取全文。先执行多引擎聚合搜索，再通过 Jina Reader 并行获取每条结果页面的完整 Markdown 内容。返回标题、URL、摘要和全文。适合需要深入了解搜索结果的场景。

Wx Search

搜索微信公众号文章。通过搜狗微信搜索引擎，支持按关键词查找公众号发布的文章，返回标题、摘要、公众号名称、发布时间。微信公众号是中文互联网最大的内容孤岛，Google/Bing 几乎无法索引。