# ToolSnap MCP

> ToolSnap MCP, an MCP server by toolsnap.app, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 38 tools.

- Canonical: https://www.anchorterminal.com/tools/toolsnap-mcp
- Markdown: https://www.anchorterminal.com/tools/toolsnap-mcp.md (~1,250 tokens)
- Slim: https://www.anchorterminal.com/tools/toolsnap-mcp.min.md (~1,180 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/toolsnap-mcp.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-04

# ToolSnap MCP

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by toolsnap.app (https://toolsnap.app/agents)
- Listed because: It's published in the registry under toolsnap.app, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Deterministic AI agent microtools, no accounts/API keys. fetch\_extract: 98% token cut. 38 tools.

## Facts

- MCP registry: `app.toolsnap/toolsnap-mcp` 1.1.0
- Endpoint: https://mcp.toolsnap.app/mcp (streamable HTTP)
- Source: https://github.com/icosaedro-git/toolsnap-mcp
- Website: https://toolsnap.app/agents
- GitHub stars: 1
- Registry entry updated: 2026-07-04

## Tools

- Tools it lists (17, about 2,040 tokens of context, `tools/list` without credentials, checked 2026-10-04 22:21 UTC):
  - `tool_catalog` (read-only): 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` (read-only): Free. Multi-tool workflow prompts (clone a site, SEO audit). No args → menu; recipe='<id>' → prompt.
  - `memory_snippet` (read-only): Free. Returns the ToolSnap habit block for your review — a summary of when these tools beat native ones, with claims you can verify yourself. Show it to your…
  - `pricing` (read-only): Free. Machine-readable pricing menu: free vs paid tools, pricing, deposit/spend flow.
  - `fetch_extract` (read-only): Fetch a URL, return clean text. Free. Median 98% fewer tokens than raw HTML. Not for JS SPAs.
  - `fetch_html` (read-only): Fetch a URL, return clean HTML (structure kept, scripts/styles stripped). Free. Site migration.
  - `html_to_markdown` (read-only): Convert a URL or raw HTML to Markdown. One of url or html. Not for JS SPAs.
  - `fetch_metadata` (read-only): Fetch a URL, extract title/description/OG/Twitter/canonical/JSON-LD. Not for body text.
  - `pdf_text_extract` (read-only): Extract text from a PDF: url or base64 data. No OCR — text-based PDFs only.
  - `csv_query` (read-only): Query a CSV: select/filter/sort/limit. One of url or csv.
  - `json_query` (read-only): Query JSON with JSONPath-lite ($.a[*].b, ..key). One of url or json.
  - `sitemap_parse` (read-only): Fetch/parse an XML sitemap into JSON. Enumerate a site's pages.
  - `rss_parse` (read-only): 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…
  - `keyword_research` (read-only): 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 —…
  - `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…
- How its tools read to an agent (0 errors, 10 warnings, 1 note, about 2,040 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC13 csv_query: headers (object with no properties)
  - warn TC13 fetch_extract: headers (object with no properties)
  - warn TC13 fetch_html: headers (object with no properties)
  - warn TC13 fetch_metadata: headers (object with no properties)
  - warn TC13 html_to_markdown: headers (object with no properties)
  - warn TC13 json_query: headers (object with no properties)
  - warn TC13 keyword_research: keywords (array with no items)
  - warn TC13 pdf_text_extract: headers (object with no properties)
  - warn TC13 use_tool: args (object with no properties)
  - warn TC18 remove_background: destructiveHint is false but the name says "remove"
  - note TC24 server: 17 of 17 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/toolsnap-mcp.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming