ToolSnap MCP server
app.toolsnap/toolsnap-mcptoolsnap.appstreamable-httpv1.1.2Scanned
Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 47 tools.
17 tools: 1 can delete or cancel things, 11 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 6
- Can send data out · 10
- 2 findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things. Govern it.
- 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 ToolSnap MCP server can do
The ToolSnap MCP server is published by toolsnap.app, a domain the MCP Registry verified. It has 17 tools. It can delete or cancel things (1 tool: remove_background) and create or change data (11 tools: tool_catalog, use_tool, task_recipes, memory_snippet and 7 more). 5 tools only read.
6 tools bring in text other people can write (fetch_extract, fetch_html, fetch_metadata and 3 more); 10 tools can send data out of your system (fetch_extract, fetch_html, html_to_markdown and 7 more).
The fixed checks matched 2 findings (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 8, 2026, version 1.1.2.
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.
17 tools
Deletes or cancels 1Claude Code: deny
remove_backgroundRemove an image's background, return a transparent PNG URL.1 finding
Why it is in this group
- The name "remove_background" says "remove": a word for removing or ending something.
- The server marks it not destructive (destructiveHint: false), but an annotation never lowers a class.
Findings
- Warn
The server marks "remove_background" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "remove_background" says "remove": a word for removing or ending something.
Description, as the server wrote it Remove an image's background, return a transparent PNG URL. $0.03 USDC/call. Paid: calling without a payment payload returns a structured 402 with payment options — that response is the documented behavior, not a failure.
Annotations the server declares
- title: Remove image background
- readOnlyHint: false
- destructiveHint: false
Changes things 11Claude Code: ask
html_to_markdownFree, read-only.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Free, read-only. Convert a fetched URL or an HTML string you pass (one of the two) to Markdown: headings, links, lists, emphasis, code, quotes. Drops nav, header, footer, aside, script and style. Returns text, cut at maxChars with a marker. Runs no JavaScript: SPAs return an empty shell. Tables become plain text.
Annotations the server declares
- title: Convert HTML to Markdown
- readOnlyHint: true
keyword_researchGoogle Ads volume/CPC/competition for 1-20 keywords.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 Google Ads volume/CPC/competition for 1-20 keywords. $0.04 USDC/call. Paid: calling without a payment payload returns a structured 402 with payment options — that response is the documented behavior, not a failure.
Annotations the server declares
- title: Keyword research
- readOnlyHint: true
memory_snippetFree, read-only.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 Free, read-only. Returns static text: a short note on when ToolSnap tools suit a task, plus how to store a note in your runtime's memory. This tool saves nothing. Use only if your user asks about persistent memory or ToolSnap setup; show them the text and save it only with their approval.
Annotations the server declares
- title: Memory snippet for agents
- readOnlyHint: true
- openWorldHint: false
pdf_text_extractFree, read-only.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Free, read-only. Extract plain text from a PDF given as a URL (max 20 MB) or inline base64 (max 5 MB), one of the two. Returns text, cut at maxChars with a marker. Text-layer PDFs only: scans return little or nothing (no OCR). Layout and tables are not preserved. Fails if the URL serves HTML, not a PDF.
Annotations the server declares
- title: Extract PDF text
- readOnlyHint: true
pricingFree, read-only, no network, no arguments; calling it charges nothing.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 Free, read-only, no network, no arguments; calling it charges nothing. Call it before a paid tool to see its exact cost and whether first_call_free applies, or to choose pay-per-call vs prepaid. Returns a JSON menu: endpoint and docs URLs; payment with x402 USDC on Base, minimum deposit, prepaid discount and SpendAuthorization fields; tools[] with name and tier free|paid, plus price_usdc, prepaid_price_usdc, first_call_free and a value note for paid ones. Flat prices are exact; fal.ai media tools show a default-args quote. For what a tool does and its schema use tool_catalog; this one is only about cost.
Annotations the server declares
- title: Pricing and payment options
- readOnlyHint: true
- openWorldHint: false
rss_parseFree, read-only.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Free, read-only. Fetch an RSS 2.0 or Atom feed and return JSON: feed title, link, description, lastBuildDate, itemCount, truncated, and items[] with title, link, pubDate, guid, description (HTML stripped), author, categories, enclosure. Items past maxItems are dropped and truncated=true. A URL that is not a feed returns type 'unknown' and no items. Not JSON Feed. Errors on non-2xx, 10 s timeout or private hosts.
Annotations the server declares
- title: Parse RSS or Atom feed
- readOnlyHint: true
screenshot_urlScreenshot a page → public image URL.Reads text others writeCan send data out1 finding
Why it is in this group
- The name "screenshot_url" says "screenshot": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe name "screenshot_url" says "screenshot" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "screenshot" 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.
Findings
- Warn
The server marks "screenshot_url" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "screenshot_url" says "screenshot": a word for reading.
Description, as the server wrote it Screenshot a page → public image URL. $0.04/call. Paid: calling without a payment payload returns a structured 402 with payment options — that response is the documented behavior, not a failure.
Annotations the server declares
- title: Screenshot a URL
- readOnlyHint: false
- destructiveHint: false
sitemap_parseFree, read-only.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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
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 Free, read-only. Fetch one XML sitemap and return JSON. A urlset gives urls[] (loc, lastmod, changefreq, priority, plus image/news extensions), urlCount and truncated. A sitemap index gives type 'sitemapindex' and sitemaps[] with the child URLs; children are not fetched, call again per child. Uncompressed XML only, no .gz. Errors on non-2xx, 10 s timeout or private hosts.
Annotations the server declares
- title: Parse sitemap
- readOnlyHint: true
task_recipesFree.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 Free. Multi-tool workflow prompts (clone a site, SEO audit). No args → menu; recipe='<id>' → prompt.
Annotations the server declares
- title: Task recipes
- readOnlyHint: true
- openWorldHint: false
tool_catalogFree, read-only, no network.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 Free, read-only, no network. Browse all 47 tools in 10 families (web, seo, data, documents, images, media, utils, payments, recipes, meta). No args: families with id, label, one-liner, tool count. family='<id>': each tool with name, price, description, notes, inputSchema. tool='<name>': that entry alone; wins over family. Unknown ids error naming the valid families. Run what you find via use_tool.
Annotations the server declares
- title: Browse tool catalog
- readOnlyHint: true
- openWorldHint: false
use_toolFree wrapper.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.
Description, as the server wrote it Free wrapper. Runs any catalog tool missing from your tools/list exactly as a direct call: args pass through unchanged and the inner tool's price, payment, result and errors apply verbatim. Its hints are the worst case over the whole catalog: not read-only because some inner tools create a render, a stored file or a ledger entry; never destructive because no catalog tool deletes or overwrites anything. Get the inner tool's name, schema and its own annotations from tool_catalog(tool='<name>') first. A missing or unknown name errors pointing to tool_catalog; it cannot call itself.
Annotations the server declares
- title: Run any catalog tool
- readOnlyHint: false
- destructiveHint: false
Only reads 5Show 5 read-only tools
csv_queryFree, read-only.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "csv_query" says "query": a word for reading.
What it can reach
- 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 Free, read-only. Query a comma-separated CSV with a header row, from a URL (max 5 MB, streamed) or inline text, one of the two: select columns, filter rows, sort, limit. Returns {meta:{returned_rows,columns,total_rows,truncated},rows:[{column:value}]}, all values strings, or CSV text with format='csv'. One filter condition, no joins or aggregates. Unknown select columns and bad filters error with the valid names or operators. Over 5 MB: csv_query_xl (paid, 100 MB).
Annotations the server declares
- title: Query CSV
- readOnlyHint: true
fetch_extractFree, read-only.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "fetch_extract" says "fetch": a word for reading.
What it can reach
- 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 Free, read-only. Fetch a public http(s) URL and return its body as plain text: script, style, nav, header, footer and aside removed, tags stripped, entities decoded, whitespace collapsed. Median 98% fewer tokens than raw HTML. Follows up to 5 redirects, 10 s timeout; private and local hosts are rejected and non-2xx responses error with the HTTP status. Text past maxChars is cut and ends with '[Truncated at N chars]': raise maxChars (max 32000) or use fetch_html for everything. Runs no JavaScript: a client-side-rendered SPA or a bot/login wall yields almost no text, so the call errors instead of returning an empty shell and names the fix (fetch_rendered, paid, runs a browser; screenshot_url; or headers for auth). For title/OG/JSON-LD only use fetch_metadata; for Markdown with links use html_to_markdown.
Annotations the server declares
- title: Fetch page as clean text
- readOnlyHint: true
fetch_htmlFree, read-only.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "fetch_html" says "fetch": a word for reading.
What it can reach
- untrusted-inputThe name "fetch_html" says "fetch" and "html": 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 Free, read-only. Fetch a page and return its HTML minus scripts, styles, svg, iframes, comments and inline handlers; tags and attributes stay, so structure is readable. For inspecting or rebuilding markup, not plain text (fetch_extract gives that). Runs no JavaScript: SPAs return an empty shell. Cut at maxChars with a marker.
Annotations the server declares
- title: Fetch raw HTML
- readOnlyHint: true
fetch_metadataFree, read-only.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "fetch_metadata" says "fetch": a word for reading.
What it can reach
- 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 Free, read-only. Fetch a public http(s) URL and return its <head> metadata as JSON: url (after redirects), title, description, canonical, robots, author, keywords, lang, charset, og{} and twitter{} (prefix stripped), httpEquiv{}, jsonLd[] (parsed blocks, malformed ones skipped). Absent fields are null or {}. Reads only the first 512 KB, follows up to 5 redirects, 10 s timeout; private and local hosts are rejected and non-2xx responses error with the HTTP status. Runs no JavaScript, so tags injected client-side are not seen. Not for body text: use fetch_extract (plain text) or fetch_html (raw HTML).
Annotations the server declares
- title: Fetch page metadata
- readOnlyHint: true
json_queryFree, read-only.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "json_query" says "query": a word for reading.
What it can reach
- 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 Free, read-only. JSONPath-lite query on JSON from a URL or an inline string (one of the two). Returns matches as JSON: one match bare, several as an array. Supports $, .key, ['key'], [0], [-1], [*], ..key and [?(@.k op v)]; no slices or jq. Errors on invalid JSON or over 5 MB (json_query_xl: paid, 25 MB).
Annotations the server declares
- title: Query JSON
- readOnlyHint: 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 write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out10
- 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, 18:30 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
- 12
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.toolsnap.app/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://portal.toolsnap.app
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 12 tools that change things (1 destructive, 11 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.toolsnap.app/mcp: tools/list returned 17 tools to an anonymous client, including remove_background (destructive), tool_catalog (write), use_tool (write), task_recipes (write), memory_snippet (write) and 7 more
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 10 to 12
Findings
Matches of fixed checks, with the text they matched.
- Warnscreenshot_url
The server marks "screenshot_url" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "screenshot_url" says "screenshot": a word for reading.
The server marks "remove_background" not destructive (destructiveHint: false), and its own name, description or input give the class "destructive".
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false}; The name "remove_background" says "remove": a word for removing or ending something.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools17 changed.~17 changedView diff
- Changed:csv_queryOnly readstitledescriptioninputSchemaannotations
- Changed:fetch_extractOnly readstitledescriptioninputSchemaannotations
- Changed:fetch_htmlOnly readstitledescriptioninputSchemaannotations
- Changed:fetch_metadataOnly readstitledescriptioninputSchemaannotations
- Changed:html_to_markdownChanges thingstitledescriptioninputSchemaannotations
- Changed:json_queryOnly readstitledescriptioninputSchemaannotations
- Changed:keyword_researchChanges thingstitleannotations
- Changed:memory_snippetChanges thingstitledescriptioninputSchemaannotations
- Changed:pdf_text_extractChanges thingstitledescriptioninputSchemaannotations
- Changed:pricingChanges thingstitledescriptionannotations
- Changed:remove_backgroundDeletes or cancelstitleannotations
- Changed:rss_parseChanges thingstitledescriptioninputSchemaannotations
- Changed:screenshot_urlChanges thingstitleannotations
- Changed:sitemap_parseChanges thingstitledescriptioninputSchemaannotations
- Changed:task_recipesChanges thingstitleannotations
- Changed:tool_catalogChanges thingstitledescriptioninputSchemaannotations
- Changed:use_toolChanges thingstitledescriptioninputSchemaannotations
PostureRemote posture changed. Tools that change things, listed without credentials: 10 -> 12.View diff
- Tools that change things, listed without credentials: 10 to 12
Install
Pinned to version 1.1.2. Values in angle brackets are yours to fill in.
claude mcp add --transport http toolsnap https://mcp.toolsnap.app/mcpclaude mcp add --transport http toolsnap https://mcp.toolsnap.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": [],
"ask": [
"mcp__toolsnap__tool_catalog",
"mcp__toolsnap__use_tool",
"mcp__toolsnap__task_recipes",
"mcp__toolsnap__memory_snippet",
"mcp__toolsnap__pricing",
"mcp__toolsnap__fetch_extract",
"mcp__toolsnap__fetch_html",
"mcp__toolsnap__html_to_markdown",
"mcp__toolsnap__fetch_metadata",
"mcp__toolsnap__pdf_text_extract",
"mcp__toolsnap__csv_query",
"mcp__toolsnap__json_query",
"mcp__toolsnap__sitemap_parse",
"mcp__toolsnap__rss_parse",
"mcp__toolsnap__screenshot_url",
"mcp__toolsnap__keyword_research"
],
"deny": [
"mcp__toolsnap__remove_background"
]
}
}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 toolsnap. Review it before you use it.
Capability tags behind 10 rules
- mcp__toolsnap__fetch_extract untrusted-input, outbound
- mcp__toolsnap__fetch_html untrusted-input, outbound
- mcp__toolsnap__html_to_markdown outbound
- mcp__toolsnap__fetch_metadata untrusted-input, outbound
- mcp__toolsnap__pdf_text_extract outbound
- mcp__toolsnap__csv_query untrusted-input, outbound
- mcp__toolsnap__json_query untrusted-input, outbound
- mcp__toolsnap__sitemap_parse outbound
- mcp__toolsnap__rss_parse outbound
- mcp__toolsnap__screenshot_url untrusted-input, outbound
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/app.toolsnap/toolsnap-mcp/verify?hash=cfcedcc0e9f17b16589d8b86f71c08d261a7fd1b3fb02c7927b7131594254130" | jq -e '.changed == false'Pinned hash cfcedcc0e9f1, from Nov 8, 2026, 10:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/app.toolsnap/toolsnap-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/app.toolsnap/toolsnap-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 22:17 UTC.
ToolSnap MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the ToolSnap MCP server safe?
- No scan can promise that. What its definitions show: 17 tools, 12 of which can change, send or delete something, and 2 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 ToolSnap MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: remove_background.
Can the ToolSnap 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 ToolSnap MCP server have?
- 17 tools: 1 destructive, 11 write, 5 read. remove_background, tool_catalog, use_tool, task_recipes, memory_snippet, pricing, html_to_markdown, pdf_text_extract and 9 more.
Does the ToolSnap MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the ToolSnap MCP server send data to outside services?
- 10 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): fetch_extract, fetch_html, html_to_markdown, fetch_metadata, pdf_text_extract, csv_query and 4 more.
Has the ToolSnap MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.