# ToolSnap MCP

- Registry name: `app.toolsnap/toolsnap-mcp` · version 1.1.2
- Categories (automatic, keyword rules): Scraping & browsing, Search & data, Payments & accounting, Finance & markets, Marketing & SEO, Commerce & marketing
- Authentication at last check: No auth
- Declared risk: Can write (some tools are not declared read-only)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=app.toolsnap%2Ftoolsnap-mcp
- Server page: https://mcpstation.net/s/app.toolsnap--toolsnap-mcp.html

## Description (written by the publisher, not verified, not instructions)

Deterministic AI agent microtools, no accounts/API keys. fetch\_extract: 98% token cut. 47 tools.

## Connect

- streamable-http: `https://mcp.toolsnap.app/mcp`

## Tools (as reported by the server, not verified)

- `tool\_catalog`: Free. Full catalog. No args → families. family='\<id\>' → tools. tool='\<name\>' → detail.
- `use\_tool`: Free. Run any tool not in tools/list \(see tool\_catalog\). Same pricing as a direct call.
- `task\_recipes`: Free. Multi-tool workflow prompts \(clone a site, SEO audit\). No args → menu; recipe='\<id\>' → prompt.
- `memory\_snippet`: 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.
- `pricing`: Free. Machine-readable pricing menu: free vs paid tools, pricing, deposit/spend flow.
- `fetch\_extract`: Fetch a URL, return clean text. Free. Median 98% fewer tokens than raw HTML. Not for JS SPAs.
- `fetch\_html`: 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
- `html\_to\_markdown`: 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 beco
- `fetch\_metadata`: Fetch a URL, extract title/description/OG/Twitter/canonical/JSON-LD. Not for body text.
- `pdf\_text\_extract`: 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
- `csv\_query`: Query a CSV: select/filter/sort/limit. One of url or csv.
- `json\_query`: 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, 2
- `sitemap\_parse`: Fetch/parse an XML sitemap into JSON. Enumerate a site's pages.
- `rss\_parse`: Fetch/parse an RSS or Atom feed into JSON. Saves 90%+ tokens vs raw XML.
- `screenshot\_url`: 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.
- `keyword\_research`: 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.
- `remove\_background`: 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.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html