Clawifi MCP server
io.github.atakanelik34/clawifi-mcpatakanelik34streamable-httpv0.4.3Scanned
Web search and page reading for AI agents: search, fetch, scrape, map and crawl, with sources.
15 tools: 7 change things and 8 only read.
- Reads private data · 0
- Reads text others write · 9
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
7 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Clawifi MCP server can do
The Clawifi MCP server is published by the GitHub account atakanelik34. It has 15 tools. It can create or change data (7 tools: scrape_url, extract_url, start_crawl, create_job and 3 more), but cannot delete data. 8 tools only read.
9 tools bring in text other people can write (fetch_url, scrape_url, extract_url and 6 more); 4 tools can send data out of your system (fetch_url, scrape_url, extract_url and 1 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in, and its tools changed 3 times since Anlyon Radar first saw them.
Last scanned Nov 21, 2026, version 0.4.3.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
15 tools
Changes things 7Claude Code: ask
accountThe signed-in account: name, plan and this month's credits.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The signed-in account: name, plan and this month's credits.
Annotations the server declares
- title: Show the account
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
create_jobRun a billable operation (fetch, batch_fetch, extract, crawl, research, ...) as a background job.Reads text others writeNo findings
Why it is in this group
- The name "create_job" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it Run a billable operation (fetch, batch_fetch, extract, crawl, research, ...) as a background job. Returns a job id for get_job.
Annotations the server declares
- title: Start a background job
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
creditsThe credit balance, what this month's calls were charged, the plan's monthly credits and when they renew.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it The credit balance, what this month's calls were charged, the plan's monthly credits and when they renew.
Annotations the server declares
- title: Show credits
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
estimateWhat 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.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- title: Estimate credits
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
extract_urlExtract structured fields from a URL: a preset (article, product, ...) or a field schema.Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Extract structured fields from a URL: a preset (article, product, ...) or a field schema.
Annotations the server declares
- title: Extract fields from a page
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
scrape_urlScrape a URL into LLM-ready formats (markdown, text, links, metadata, html, screenshot, state_json).Reads text others writeCan send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "scrape_url" says "scrape": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "scrape": it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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 content_status.
Annotations the server declares
- title: Scrape a page
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
start_crawlStart a crawl from a seed URL in the background.Reads text others writeNo findings
Why it is in this group
- The name "start_crawl" says "start": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "start_crawl" says "crawl": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it Start a crawl from a seed URL in the background. Returns a crawl id for get_crawl.
Annotations the server declares
- title: Start a crawl
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 8Show 8 read-only tools
fetch_urlFetch one URL (page or PDF) as clean markdown with route diagnostics.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "fetch_url" says "fetch": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "fetch_url" says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "fetch" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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.
Annotations the server declares
- title: Fetch a page
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_crawlStatus and pages of a crawl started with start_crawl.Reads text others writeNo findings
Why it is in this group
- The name "get_crawl" says "get": a word for reading.
What it can reach
- untrusted-inputThe name "get_crawl" says "crawl": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it Status and pages of a crawl started with start_crawl.
Annotations the server declares
- title: Get crawl results
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_jobStatus and result of a job started with create_job.No findings
Why it is in this group
- The name "get_job" says "get": a word for reading.
Description, as the server wrote it Status and result of a job started with create_job.
Annotations the server declares
- title: Get job results
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_historyThe account's past calls, newest first; operation filters by name (e.g.No findings
Why it is in this group
- The name "list_history" says "list": a word for reading.
Description, as the server wrote it The account's past calls, newest first; operation filters by name (e.g. search_free).
Annotations the server declares
- title: List past calls
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_monitorsThe account's Evidence Monitor checks.No findings
Why it is in this group
- The name "list_monitors" says "list": a word for reading.
Description, as the server wrote it The account's Evidence Monitor checks.
Annotations the server declares
- title: List monitors
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
map_siteList a site's discoverable URLs (sitemap, robots, links) from a seed URL; search filters them.Reads text others writeCan send data outNo findings
Why it is in this group
- The description's first verb is "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "list" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it List a site's discoverable URLs (sitemap, robots, links) from a seed URL; search filters them.
Annotations the server declares
- title: Map a site
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
read_artifactRead 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 ma…Reads text others writeNo findings
Why it is in this group
- The name "read_artifact" says "read": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Read a stored page
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
search_freeSearch the web and return ranked results: url, title, snippet, rank, and published_at when the engine gives a date.Reads text others writeNo findings
Why it is in this group
- The name "search_free" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "search" and "web": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Search the web
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write9
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:02 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 7
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://api.clawifi.dev/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://api.clawifi.dev
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.clawifi.dev/mcp: tools/list returned 15 tools to an anonymous client, including scrape_url (write), extract_url (write), start_crawl (write), create_job (write), estimate (write) and 2 more
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 1 to 7
- RFC 9728 protected resource metadata: none to https://api.clawifi.dev/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://api.clawifi.dev
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:fetch_urlOnly readsdescriptioninputSchema
- Changed:scrape_urlChanges thingsdescription
- Changed:search_freeOnly readsdescription
Tools11 added.+11 addedView diff
- Added:accountChanges things
- Added:create_jobChanges things
- Added:creditsChanges things
- Added:estimateChanges things
- Added:extract_urlChanges things
- Added:get_crawlOnly reads
- Added:get_jobOnly reads
- Added:list_historyOnly reads
- Added:list_monitorsOnly reads
- Added:read_artifactOnly reads
- Added:start_crawlChanges things
PostureRemote posture changed. Tools that change things, listed without credentials: 1 -> 7; RFC 9728 protected resource metadata: none -> https://api.clawifi.dev/.well-known/oauth-protected-resource/mcp; Authorization servers: none -> https://api…View diff
- Tools that change things, listed without credentials: 1 to 7
- RFC 9728 protected resource metadata: none to https://api.clawifi.dev/.well-known/oauth-protected-resource/mcp
- Authorization servers: none to https://api.clawifi.dev
- Dynamic client registration: not observed to yes
- Client ID metadata documents: not observed to yes
Tools4 changed.~4 changedView diff
- Changed:fetch_urlOnly readstitleannotations
- Changed:map_siteOnly readstitleannotations
- Changed:scrape_urlChanges thingstitleannotations
- Changed:search_freeOnly readstitleannotations
Install
Pinned to version 0.4.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http clawifi https://api.clawifi.dev/mcpclaude mcp add --transport http clawifi https://api.clawifi.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__clawifi__search_free",
"mcp__clawifi__get_crawl",
"mcp__clawifi__read_artifact",
"mcp__clawifi__get_job",
"mcp__clawifi__list_history",
"mcp__clawifi__list_monitors"
],
"ask": [
"mcp__clawifi__fetch_url",
"mcp__clawifi__scrape_url",
"mcp__clawifi__extract_url",
"mcp__clawifi__map_site",
"mcp__clawifi__start_crawl",
"mcp__clawifi__create_job",
"mcp__clawifi__estimate",
"mcp__clawifi__account",
"mcp__clawifi__credits"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as clawifi. Review it before you use it.
Capability tags behind 9 rules
- mcp__clawifi__fetch_url untrusted-input, outbound
- mcp__clawifi__scrape_url untrusted-input, outbound
- mcp__clawifi__extract_url untrusted-input, outbound
- mcp__clawifi__search_free untrusted-input
- mcp__clawifi__map_site untrusted-input, outbound
- mcp__clawifi__start_crawl untrusted-input
- mcp__clawifi__get_crawl untrusted-input
- mcp__clawifi__read_artifact untrusted-input
- mcp__clawifi__create_job untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.atakanelik34/clawifi-mcp/verify?hash=dea44e62de60e8d366bb6f7b6661ff5e50023fb45f8490c3f9820cd5427319e3" | jq -e '.changed == false'Pinned hash dea44e62de60, from Nov 21, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.atakanelik34/clawifi-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.atakanelik34/clawifi-mcp)Source: MCP Registry · repository. Synced Nov 21, 2026, 02:17 UTC.
Clawifi MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Clawifi MCP server safe?
- No scan can promise that. What its definitions show: 15 tools, 7 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Clawifi MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Clawifi MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Clawifi MCP server have?
- 15 tools: 7 write, 8 read. scrape_url, extract_url, start_crawl, create_job, estimate, account, credits, fetch_url and 7 more.
Does the Clawifi MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Clawifi MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): fetch_url, scrape_url, extract_url and map_site.
Has the Clawifi MCP server changed its tools?
- Yes, 3 times since Anlyon Radar started tracking it, most recently on Nov 10, 2026. Every change is on this page and in its Atom feed.