SmartFetch MCP server
io.github.Friezaaaa/smartfetchFriezaaaastreamable-httpv1.15.0Scanned
HTML/PDF/Markdown, browser render, screenshots, site intel, URL map & batch via Base/Solana x402.
12 tools: 4 change things and 8 only read.
- Reads private data · 1
- Reads text others write · 7
- Can send data out · 8
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 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 SmartFetch MCP server can do
The SmartFetch MCP server is published by the GitHub account Friezaaaa. It has 12 tools. It can create or change data (4 tools: webpage_to_markdown, extract_webpage_text, render_webpage and map_website), but cannot delete data. 8 tools only read.
1 tool reads private data (batch_fetch_webpages); 7 tools bring in text other people can write (fetch_webpage, screenshot_webpage, inspect_webpage and 4 more); 8 tools can send data out of your system (fetch_webpage, webpage_to_markdown, extract_webpage_text and 5 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
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 2 times since Anlyon Radar first saw them.
Last scanned Nov 18, 2026, version 1.15.0.
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.
12 tools
Changes things 4Claude Code: ask
extract_webpage_textToken-efficient extractor that returns ONLY clean plain text and core metadata from a public webpage or PDF (omits Markdown formatting, links array, and raw HTML).Can 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.
What it can reach
- 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 Token-efficient extractor that returns ONLY clean plain text and core metadata from a public webpage or PDF (omits Markdown formatting, links array, and raw HTML). Use when you only need plain readable text.
map_websiteWebsite URL discovery and sitemap mapper.Can 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.
What it can reach
- 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 Website URL discovery and sitemap mapper. Discovers and maps internal URLs across a website using robots.txt, XML sitemaps (including nested sitemap indexes), and HTML links, with optional search filtering and subdomain support.
render_webpageForced headless Chromium browser renderer for JavaScript-heavy SPAs and dynamic webpages.Can 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.
What it can reach
- 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 Forced headless Chromium browser renderer for JavaScript-heavy SPAs and dynamic webpages. Always executes Tier 3 isolated browser rendering and returns the post-JS rendered HTML DOM alongside extracted text, Markdown, links, and metadata. Do not use for PDFs or static pages (use fetch_webpage instead).
webpage_to_markdownToken-efficient converter that returns ONLY clean Markdown and core metadata from a public webpage or PDF (omits duplicate plain text, links array, and raw HTML).Can 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.
What it can reach
- 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 Token-efficient converter that returns ONLY clean Markdown and core metadata from a public webpage or PDF (omits duplicate plain text, links array, and raw HTML). Use when you only need Markdown.
Only reads 8Show 8 read-only tools
batch_fetch_webpagesParallel batch webpage and document retrieval tool.Reads private dataReads text others writeCan send data outNo findings
Why it is in this group
- The name "batch_fetch_webpages" says "fetch": a word for reading.
What it can reach
- private-dataThe description's first sentence says "document": it reads documents.
- untrusted-inputThe name "batch_fetch_webpages" says "fetch" and "webpage": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "webpage": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.urls), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.urls): 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 Parallel batch webpage and document retrieval tool. Fetches up to 5 public URLs concurrently with fair settlement (returns 502 without settling if all fail), VPS browser concurrency protection, and native Markdown/plain text output.
fetch_webpagePrimary webpage and PDF retrieval tool.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "fetch_webpage" says "fetch": a word for reading.
What it can reach
- untrusted-inputThe name "fetch_webpage" says "fetch" and "webpage": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "webpage": 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 Primary webpage and PDF retrieval tool. Use by default to fetch any public HTTP/HTTPS webpage or PDF and return clean text, Markdown, links, and metadata. Uses fast HTTP first and automatically falls back to an isolated headless browser for JavaScript-rendered pages. (Use webpage_to_markdown or extract_webpage_text for token-saving single-format output, or render_webpage when you need raw rendered HTML DOM.)
inspect_webpageStructured webpage and site intelligence and SEO inspection tool for any public URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "inspect_webpage" says "inspect": a word for reading.
What it can reach
- untrusted-inputThe name "inspect_webpage" says "inspect" and "webpage": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "webpage": 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 Structured webpage and site intelligence and SEO inspection tool for any public URL. Extracts comprehensive metadata, OpenGraph, Twitter cards, JSON-LD schemas, contact details (emails, phones, social links), tech stack detection, security headers, and document outline.
screenshot_webpageBrowser-based webpage screenshot capture tool.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "screenshot_webpage" says "screenshot": a word for reading.
What it can reach
- untrusted-inputThe name "screenshot_webpage" says "screenshot" and "webpage": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "browser": 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 Browser-based webpage screenshot capture tool. Captures high-resolution JPEG or PNG screenshots of public webpages using isolated headless Chromium with configurable desktop/mobile viewport and optional full-page capture.
search_and_fetchSearch the web and automatically fetch clean Markdown content for the top matching pages in one call.Reads text others writeNo findings
Why it is in this group
- The name "search_and_fetch" says "search": a word for reading.
What it can reach
- 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 automatically fetch clean Markdown content for the top matching pages in one call.
search_leadsB2B Enriched Lead Generator.No findings
Why it is in this group
- The name "search_leads" says "search": a word for reading.
Description, as the server wrote it B2B Enriched Lead Generator. Searches Google Maps or Web via Serper and enriches each company website with emails, phones, social links, tech stack, and domain/MX intelligence.
search_webLive web, news, and places search powered by Serper (with Exa fallback for web).Reads text others writeNo findings
Why it is in this group
- The name "search_web" says "search": a word for reading.
What it can reach
- untrusted-inputThe name "search_web" says "search" and "web": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
Description, as the server wrote it Live web, news, and places search powered by Serper (with Exa fallback for web). Returns structured titles, URLs, snippets, and metadata.
search_x_postsLive X/Twitter post search returning normalized posts, engagement metrics, author details, and pagination cursor.Reads text others writeNo findings
Why it is in this group
- The name "search_x_posts" says "search": a word for reading.
What it can reach
- untrusted-inputThe name "search_x_posts" says "search" and "post": it reads posts, which other people can write.
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it Live X/Twitter post search returning normalized posts, engagement metrics, author details, and pagination cursor.
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.
56 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out8
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__smartfetch__batch_fetch_webpages"
]
}
}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, 18:58 UTC, unchanged since Nov 20, 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
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://smartfetch-production-ea53.up.railway.app/mcp: tools/list returned 12 tools to an anonymous client, including webpage_to_markdown (write), extract_webpage_text (write), render_webpage (write), map_website (write)
Posture changes
- Nov 20, 2026
- HTTP status of an anonymous initialize: 404 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 4
- Protocol version: none to 2025-06-18
- Nov 6, 2026
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
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.
PostureRemote posture changed. HTTP status of an anonymous initialize: 404 -> 200; tools/list served without credentials: no -> yes; Tools that change things, listed without credentials: 0 -> 4 (and 1 more).View diff
- HTTP status of an anonymous initialize: 404 to 200
- tools/list served without credentials: no to yes
- Tools that change things, listed without credentials: 0 to 4
- Protocol version: none to 2025-06-18
Tools4 added, 6 changed.+4 added~6 changedView diff
- Added:search_and_fetchOnly reads
- Added:search_leadsOnly reads
- Added:search_webOnly reads
- Added:search_x_postsOnly reads
- Changed:extract_webpage_textChanges thingsinputSchema
- Changed:fetch_webpageOnly readsinputSchema
- Changed:inspect_webpageOnly readsinputSchema
- Changed:render_webpageChanges thingsinputSchema
- Changed:screenshot_webpageOnly readsinputSchema
- Changed:webpage_to_markdownChanges thingsinputSchema
Tools4 added, 4 changed.+4 added~4 changedView diff
- Added:batch_fetch_webpagesOnly reads
- Added:inspect_webpageOnly reads
- Added:map_websiteChanges things
- Added:screenshot_webpageOnly reads
- Changed:extract_webpage_textChanges thingsdescriptioninputSchema
- Changed:fetch_webpageOnly readsdescriptioninputSchema
- Changed:render_webpageChanges thingsdescriptioninputSchema
- Changed:webpage_to_markdownChanges thingsdescriptioninputSchema
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 404; tools/list served without credentials: yes -> no; Tools that change things, listed without credentials: 3 -> 0 (and 1 more).View diff
- HTTP status of an anonymous initialize: 200 to 404
- tools/list served without credentials: yes to no
- Tools that change things, listed without credentials: 3 to 0
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.15.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http smartfetch https://smartfetch-production-ea53.up.railway.app/mcpclaude mcp add --transport http smartfetch https://smartfetch-production-ea53.up.railway.app/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__smartfetch__search_web",
"mcp__smartfetch__search_and_fetch",
"mcp__smartfetch__search_leads",
"mcp__smartfetch__search_x_posts"
],
"ask": [
"mcp__smartfetch__fetch_webpage",
"mcp__smartfetch__webpage_to_markdown",
"mcp__smartfetch__extract_webpage_text",
"mcp__smartfetch__render_webpage",
"mcp__smartfetch__screenshot_webpage",
"mcp__smartfetch__inspect_webpage",
"mcp__smartfetch__batch_fetch_webpages",
"mcp__smartfetch__map_website"
],
"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 smartfetch. Review it before you use it.
Capability tags behind 11 rules
- mcp__smartfetch__fetch_webpage untrusted-input, outbound
- mcp__smartfetch__webpage_to_markdown outbound
- mcp__smartfetch__extract_webpage_text outbound
- mcp__smartfetch__render_webpage outbound
- mcp__smartfetch__screenshot_webpage untrusted-input, outbound
- mcp__smartfetch__inspect_webpage untrusted-input, outbound
- mcp__smartfetch__batch_fetch_webpages private-data, untrusted-input, outbound
- mcp__smartfetch__map_website outbound
- mcp__smartfetch__search_web untrusted-input
- mcp__smartfetch__search_and_fetch untrusted-input
- mcp__smartfetch__search_x_posts 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.Friezaaaa/smartfetch/verify?hash=de6ca445f53a8d4017209141c2e408c118b4d9a1dd5b9e486c49d93e9b7fd29d" | jq -e '.changed == false'Pinned hash de6ca445f53a, from Nov 18, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Friezaaaa/smartfetch/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Friezaaaa/smartfetch)Source: MCP Registry · repository. Synced Nov 18, 2026, 17:17 UTC.
SmartFetch MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the SmartFetch MCP server safe?
- No scan can promise that. What its definitions show: 12 tools, 4 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 SmartFetch MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the SmartFetch 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 SmartFetch MCP server have?
- 12 tools: 4 write, 8 read. webpage_to_markdown, extract_webpage_text, render_webpage, map_website, fetch_webpage, screenshot_webpage, inspect_webpage, batch_fetch_webpages and 4 more.
Does the SmartFetch MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the SmartFetch MCP server send data to outside services?
- 8 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): fetch_webpage, webpage_to_markdown, extract_webpage_text, render_webpage, screenshot_webpage, inspect_webpage and 2 more.
Has the SmartFetch MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 18, 2026. Every change is on this page and in its Atom feed.