ToolSnap MCP
app.toolsnap/toolsnap-mcp · v1.1.0 · MCP 2025-11-25
Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 38 tools.
Reachability
reachable
checked 2026-07-14 03:05 UTC
Registry status active
Tools pinned 18
d2f5c227f56a
Tools last changed
unchanged since first capture 2026-07-14
Provenance
Registry namespace app.toolsnap
(domain verified by the official registry)
Repository
github.com/icosaedro-git/toolsnap-mcp
Website
https://toolsnap.app/agents
Remote endpoints
https://mcp.toolsnap.app/mcp (streamable-http)
Observed changes
| When (UTC) | Event | Detail |
|---|---|---|
| 2026-07-14 03:05 | first capture | 18 tools pinned |
Pinned tool definitions (18)
| Tool | Description |
|---|---|
| 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. ToolSnap habit block + save instruction for your harness's memory. |
| 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 | Fetch a URL, return clean HTML (structure kept, scripts/styles stripped). Free. Site migration. |
| html_to_markdown | Convert a URL or raw HTML to Markdown. One of url or html. Not for JS SPAs. |
| fetch_metadata | Fetch a URL, extract title/description/OG/Twitter/canonical/JSON-LD. Not for body text. |
| fetch_structured | Fetch a URL, extract JSON Schema fields from its JSON-LD/OG/microdata. Deterministic. |
| pdf_text_extract | Fetch a PDF by URL, extract text. No OCR — text-based PDFs only. |
| csv_query | Query a CSV: select/filter/sort/limit. Provide exactly one source: url (to fetch) or csv (raw text). Prefer url when the file is already hosted — the fetch + query run server-side and only the result returns, so a large CSV never passes... |
| json_query | Query JSON with JSONPath-lite ($.a[*].b, ..key). One of url or json. |
| 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. |
| keyword_research | Google Ads volume/CPC/competition for 1-20 keywords. $0.04 USDC/call. |
| remove_background | Remove an image's background, return a transparent PNG URL. $0.03 USDC/call. |
Status badge
[](https://toolpin.dev/servers/app.toolsnap/toolsnap-mcp)
Maintain this server? Add the badge to your README — it links your users to this live status page.