Clawifi

Connect Remote server

claude mcp add --transport http clawifi-mcp https://api.clawifi.dev/mcp --header "Authorization: Bearer <YOUR_API_KEY>"

{
  "mcpServers": {
    "clawifi-mcp": {
      "url": "https://api.clawifi.dev/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}

{
  "servers": {
    "clawifi-mcp": {
      "type": "http",
      "url": "https://api.clawifi.dev/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}

Settings > Connectors > Add custom connector
URL: https://api.clawifi.dev/mcp

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools 15 found in our last check

• fetch_url

  Fetch one URL (page or PDF) as clean markdown with route diagnostics. query returns only the top_k passages that answer it. content_scope="full" returns the whole page text, not just the main content. force_browser renders it in a browser (3 credits instead of 1); render="auto"…

• scrape_url

  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. Returns formats.<name>, metadata (title, final_url, canonical_url, excerpt), published_at/modified_at and…

• extract_url

  Extract structured fields from a URL: a preset (article, product, ...) or a field schema.

• search_free

  Search the web and return ranked results: url, title, snippet, rank, and published_at when the engine gives a date. No page text; read a result with fetch_url. Fields: https://clawifi.dev/docs/search.

• map_site

  List a site's discoverable URLs (sitemap, robots, links) from a seed URL; search filters them.

• start_crawl

  Start a crawl from a seed URL in the background. Returns a crawl id for get_crawl.

• get_crawl

  Status and pages of a crawl started with start_crawl.

• read_artifact

  Read a stored artifact of the account by its id, such as a page get_crawl or fetch_url lists: an HTML page comes back as markdown (as_markdown=false for the raw HTML), capped at max_chars. Free.

• create_job

  Run a billable operation (fetch, batch_fetch, extract, crawl, research, ...) as a background job. Returns a job id for get_job.

• get_job

  Status and result of a job started with create_job.

• list_history

  The account's past calls, newest first; operation filters by name (e.g. search_free).

• list_monitors

  The account's Evidence Monitor checks.

• estimate

  What a call would cost in credits before running it: minimum (what the balance must cover), maximum or a caveat, what raises it, the balance and would_402. operation is a tool name (fetch_url, start_crawl, research, ...) or a job operation; args are that call's arguments. Runs n…

• account

  The signed-in account: name, plan and this month's credits.

• credits

  The credit balance, what this month's calls were charged, the plan's monthly credits and when they renew.

Headers

Details

More search and web servers See all

• Live Sports Scores & Betting Odds MCP Server

  Keyless sports scores, betting odds, injuries & news: NFL NBA MLB NHL soccer. No API key.

• Knowra

  Search arXiv papers and read Scout reports with methods, evidence and verification points.

• Contract Compass

  Korean public procurement law: rule-engine rulings, statutes search, live court precedents

• Korea Realty

  Korean real estate: court auctions, 10M+ MOLIT records, subscription notice facts, loan/DSR rules

• 校招宝 · 中国校园招聘岗位数据

  中国校园招聘（秋招/春招/实习/提前批）在招岗位、企业档案、投递截止与求职攻略数据。免 API Key、免注册、只读。

• IBDÅ

  Ask about IBDÅ, a design-led R&D and innovation studio in Dubai, and prepare a project enquiry.