A
licenseNot graded
qualityD
maintenanceProvides web search and content extraction for AI agents.
MIT
Clawifi
Server Details
Agent-native internet gateway: typed search, fetch, scrape, crawl, and extract via the Clawifi API.
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- ReARCLabs/clawifi-mcp
- GitHub Stars
- 0
- Server Listing
- clawifi-mcp
- ChatGPT
- –
- Claude
- Clawifi
TDQS
B3.1/5.0
Scored across 15 tools
Disambiguation3/5
Several tools overlap in purpose: fetch_url and scrape_url both fetch URLs and can return markdown/passage excerpts, while create_job can run crawl-like operations alongside the dedicated start_crawl/get_crawl pair. Descriptions do help distinguish the main intent, but an agent still faces real ambiguity in common workflows.
Naming Consistency3/5
Most names use snake_case and a verb_noun pattern, but several are noun-only (account, credits) or verb-only (estimate), and the job/crawl naming is split across create_job/get_job and start_crawl/get_crawl. The convention is readable but not fully consistent.
Tool Count5/5
Fifteen tools is within the expected range for a web data platform with search, fetch, scrape, extract, crawl, job, billing, and artifact operations. The count is well-scoped rather than excessive.
Completeness3/5
Core workflows are well covered, but there are notable lifecycle gaps: crawls and jobs can be started/checked but not cancelled, and list_monitors has no create/update/delete counterparts. These gaps will limit some agent workflows around monitoring and job control.
Available Tools
15 toolsaccountShow the accountARead-onlyIdempotentInspect
The signed-in account: name, plan and this month's credits.
Inputs: no named parameters. Returns: object
create_jobStart a background jobBInspect
Run a billable operation (fetch, batch_fetch, extract, crawl, research, ...) as a background job. Returns a job id for get_job.
Inputs: payload (required), operation (required). Returns: object
creditsShow creditsBRead-onlyIdempotentInspect
The credit balance, what this month's calls were charged, the plan's monthly credits and when they renew.
Inputs: no named parameters. Returns: object
estimateEstimate creditsARead-onlyIdempotentInspect
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 nothing and charges nothing.
Inputs: operation (required), args. Returns: object
extract_urlExtract fields from a pageCRead-onlyIdempotentInspect
Extract structured fields from a URL: a preset (article, product, ...) or a field schema.
Inputs: url (required), preset, schema, timeout_seconds. Returns: object
fetch_urlFetch a pageARead-onlyIdempotentInspect
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" does that only for a JavaScript shell. Returns data.title, data.content_markdown, data.published_at/modified_at when the page gives them, data.fetched_at and content_status (ok, thin, blocked, needs_javascript, not_found); fields: https://clawifi.dev/docs/fetch.
Inputs: url (required), query, top_k, render, +5 more. Returns: object
get_crawlGet crawl resultsARead-onlyIdempotentInspect
Status and pages of a crawl started with start_crawl.
Inputs: crawl_id (required). Returns: object
get_jobGet job resultsARead-onlyIdempotentInspect
Status and result of a job started with create_job.
Inputs: job_id (required). Returns: object
list_historyList past callsCRead-onlyIdempotentInspect
The account's past calls, newest first; operation filters by name (e.g. search_free).
Inputs: limit, cursor, operation. Returns: object
list_monitorsList monitorsCRead-onlyIdempotentInspect
The account's Evidence Monitor checks.
Inputs: limit. Returns: object
map_siteMap a siteBRead-onlyIdempotentInspect
List a site's discoverable URLs (sitemap, robots, links) from a seed URL; search filters them.
Inputs: url (required), search, max_urls. Returns: object
read_artifactRead a stored pageARead-onlyIdempotentInspect
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.
Inputs: artifact_id (required), max_chars, as_markdown. Returns: object
scrape_urlScrape a pageBRead-onlyIdempotentInspect
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., metadata (title, final_url, canonical_url, excerpt), published_at/modified_at and content_status.
Inputs: url (required), mode, query, top_k, +3 more. Returns: object
search_freeSearch the webARead-onlyIdempotentInspect
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.
Inputs: query (required), time_range, max_results, include_domains. Returns: object
start_crawlStart a crawlBInspect
Start a crawl from a seed URL in the background. Returns a crawl id for get_crawl.
Inputs: seed_url (required), max_depth, max_pages. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Web data for agents. Extract web pages, crawl websites, discover URLs, and search the web.
Web scraping, search, crawling, structured extraction and research for AI agents.
Web search and page fetch for AI agents. Results come from a shared cache; cached calls cost less.
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
Related MCP Servers
FlyCrawl MCP Serverofficial
AlicenseAqualityCmaintenanceEnables Claude Desktop, Cursor AI, Windsurf, and autonomous LLM agents to scrape, crawl, map, search, and extract validated JSON from live web pages with dynamic rendering, anti-bot bypass, and Markdown conversion.511 npmMIT- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search the web, read and extract content from webpages, fetch JSON from REST APIs, and collect links while bypassing anti-bot protections.44 npmISC
- AlicenseAqualityCmaintenanceEnables AI agents to fetch, crawl, extract, and search web content through a unified set of tools, with automatic routing to specialized backends.4MIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.