io.github.atakanelik34由 GitHub 账号 atakanelik34 发布v0.4.0更新于 Oct 27, 2026
Agent-native internet gateway: typed search, fetch, scrape, crawl, and extract via the Clawifi API.
Clawifi 是一个托管的网页搜索与页面读取网关，让助手搜索网页、把页面和 PDF 抓取为 markdown、抓取结构化内容并列出站点 URL。
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。
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.atakanelik34%2Fclawifi-mcp/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。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"clawifi": {
"type": "http",
"url": "https://api.clawifi.dev/mcp"
}
}
}[PyPI] [Python] [License] [MCP] [GitHub stars]
Official Python SDK, CLI, and MCP server for Clawifi, web search and page reading for AI agents: search many engines as one, read pages and PDFs, map and crawl sites, and get back only the passages that answer the question, each with its source. One typed API and MCP surface for all of it.
This package is a thin client over the hosted Clawifi API (hosted API version 1.7.2 at time of release); the Clawifi server is not included. Docs, pricing and status: clawifi.dev/docs · clawifi.dev/pricing · clawifi.dev/status · clawifi.dev/security.
[Add to Cursor] [Install in VS Code]
Both add the hosted remote server https://api.clawifi.dev/mcp. No key needed to try: 4 tools, 50 calls a day per address. Add your API key for the full toolset (get a free key).
This creates an account, grants 1,000 free credits, and prints an API key. Export it:
finds the MCP clients installed on this machine (Claude Code, Codex, Cursor, Claude Desktop, VS Code) and prints, for each one, the install line for the local server (clawifi-mcp, stdio) and for the remote server, followed by a first call to try. It only prints; it never shows your key, only $CLAWIFI_API_KEY or a masked clawifi_live_****. clawifi init --all shows every client, found or not.
To have it edit a config file for you:
--write asks before it changes anything and copies the existing file to <file>.bak-<timestamp> first. Claude Code, Codex and VS Code have their own install commands, which init prints.
For Claude Code, for example:
The local MCP server runs as:
reading CLAWIFI_API_KEY from the environment. clawifi mcp config prints a minimal config for it. Every tool carries a title and the MCP hints readOnlyHint, destructiveHint, idempotentHint and openWorldHint; none is destructive.
The billable tools (fetch, scrape, extract, map_site, crawl, search_free) take their common options as parameters and any other API field in options, which is merged into the request body. They refuse dry_run: use the estimate tool to price a call. Arguments a tool does not declare are refused rather than ignored.
Clawifi also runs a hosted MCP server, so nothing needs installing:
https://api.clawifi.dev/mcp (streamable HTTP)Authorization: Bearer <your key>, or the X-Clawifi-Api-Key: <your key> headerThe old host api.clawifi.qzz.io (API and /mcp) keeps working, so CLAWIFI_API_BASE=https://api.clawifi.qzz.io and existing remote configs need no change.
Without a key the remote server offers a keyless tier of four tools, search_free, fetch_url, scrape_url and map_site, at 12 calls a minute and 50 a day per address. With a key you get the full tool list.
Calls are charged per operation (a plain fetch is 1 credit, a browser render 3, a crawl 1 per page, and so on). See clawifi.dev/pricing, or print the current table, which needs no key:
The credits MCP tool and client.credits() show your own usage and balance instead.
An async client is also available as clawifi.AsyncClawifi.
search_content searches and reads the top results; it is compact by default and full=True returns the full output:
Responses are returned as the API sends them, so fields such as published_at, modified_at and fetched_at come through untouched.
estimate() and dry_run=True work for fetch, scrape, extract, map, crawl, search_free and search_content. Before the first dry run the client checks the API version at /product/manifest; an API older than 1.7.0 would ignore dry_run and run (and bill) the call, so the client raises ClawifiDryRunUnsupportedError and sends nothing. Pre-releases such as 1.7.0rc1 count as older than 1.7.0.
dry_run is sent only when it is True, and only as the JSON boolean true: a normal call, or dry_run=False, has no dry_run key in its body, and a value that is not a bool raises TypeError before anything is sent. The API answers any dry_run key (even false) on a route that cannot dry-run with a 422, so schema_assist drops dry_run=False and refuses dry_run=True.
The estimate MCP tool does the same from an agent: estimate(operation="fetch", args={"url": "https://example.com"}).
A 429 raises ClawifiAPIError with retry_after (seconds, from the Retry-After header) and limit_scope (which limit was hit, from details.limit_scope). Retryable calls wait out a Retry-After of up to 10 seconds before retrying; a longer one is raised straight away.
See clawifi.dev/docs for the full API reference, MCP tool list, and CLI command reference.
MIT
来源：README.md，提交 7a99f3c
Fetch a page
Fetch one URL (page or PDF) as clean markdown with route diagnostics. query returns only the top_k passages that answer it. force_browser renders it in a browser (3 credits instead of 1).
url必填querytop_kmax_pagesforce_browsertarget_selectortimeout_secondsScrape a page
Scrape a URL into LLM-ready formats (markdown, text, links, metadata, html, screenshot, state_json). query keeps only the top_k passages of markdown and text that answer it.
url必填modequerytop_kformatstarget_selectortimeout_secondsSearch the web
Search the web and return ranked results (title, URL, snippet).
query必填time_rangemax_resultsinclude_domainsMap a site
List a site's discoverable URLs (sitemap, robots, links) from a seed URL; search filters them.
url必填searchmax_urls已满足适用检查项的 100%
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。
pip install clawificlawifi signup --email [email protected] --password "a strong password"export CLAWIFI_API_KEY="clawifi_live_..."clawifi quicktest --url https://example.comclawifi initclawifi init --write cursor # ~/.cursor/mcp.json, stdio entryclawifi init --write cursor --remote # ~/.cursor/mcp.json, remote entryclawifi init --write claude-desktop # claude_desktop_config.json, stdio entry# local (stdio)claude mcp add --env CLAWIFI_API_KEY=$CLAWIFI_API_KEY --transport stdio clawifi -- clawifi-mcp# remoteclaude mcp add --transport http clawifi https://api.clawifi.dev/mcp --header "Authorization: Bearer $CLAWIFI_API_KEY"clawifi-mcpclawifi creditsfrom clawifi import Clawifi
client = Clawifi() # reads CLAWIFI_API_KEY from the environmentpage = client.fetch("https://example.com")print(page["success"])results = client.search_content("agent memory benchmarks", full=True)quote = client.estimate("fetch", url="https://example.com")# {"dry_run": true, "route": "POST /fetch", "estimate": {"minimum": ..., "maximum": ..., "raises": [...]},# "balance": ..., "would_402": ..., "would_429": ..., "binding_limit": ..., "charged": 0}client.crawl("https://example.com", max_pages=50, dry_run=True)