usestring/string-ai-mcp

The official Model Context Protocol (MCP) server for
String AI's Web Access API. Search the web, fetch any URL or send it a
request, and map a site's URLs — all returned as clean, LLM-ready Markdown. Connect any
MCP-compatible client — VS Code, Cursor, Windsurf, Claude Desktop, and more.
Tools
| Tool | Description |
| --------------------- | ------------------------------------------------------------------------------- |
| web_access_fetch | Fetch one URL and get clean, LLM-ready Markdown back |
| web_access_product_help | Ask about String products or services; get one source (two for comparisons), with a shared 4 KiB excerpt budget and source links |
| web_access_request | Send a POST, PUT or PATCH with a body to a URL |
| web_access_search | Search the web: ranked results plus the knowledge panel, AI overview, local pack and other surfaces Google rendered; optional searchCount (1–300) pages Google; searchType searches Google's images, videos, shopping, books, places or forums tab; safeSearch, includeOmittedResults, autocorrect, restrictCountry and verbatim filter it; page, dateRange and sortBy refine a Google search; format is "structured" (JSON, the default and recommended) or "raw" (the Google results page as HTML, one page per call; page only, searchCount is rejected with raw) |
| web_access_sitemap | Crawl a site and map its URLs as an asynchronous job, driven by action |
| web_access_report | Send one redacted, credit-free failure diagnostic to String support |
web_access_fetch, web_access_search, and web_access_product_help are read-only. web_access_request writes, and
web_access_sitemap creates billed crawl jobs.
> The six-tool shape above is what the hosted server at https://mcp.usestring.ai/v1/mcp
> serves. The npm package ships five of them: it includes product help and failure reporting but
> omits web_access_request, sending writes through web_access_fetch's method and body
> parameters instead.
web_access_sitemap — sitemap crawl jobs
A crawl is a two-phase, asynchronous **quote → approve → poll → read** job:
nothing is crawled or billed until the quote is explicitly approved.
| action | What it does |
| --------- | -------------------------------------------------------------------------------------------------- |
| submit | Quote a crawl (url required; maxPages ≤ 10000 default 10, maxDepth ≤ 100 default 2, pathPrefix, budgetUsd, useSitemap optional). Returns jobId + estimatedCostUsd + estimatedPages, status awaiting_approval. |
| approve | Billing consent — starts the crawl. 402 = insufficient funds; 409 partial_state = retry approve. |
| status | Poll progress: awaiting_approval → running (pending/processed) → completed \| failed \| canceled \| token_cap_exceeded; partial_state = retry approve. Returns counts only — URLs come from results. |
| results | Paginated discovered URLs (limit ≤ 5000 default 1000, offset). Durable after completion; per-URL discoveredUrls is only present for ~1h. |
| cancel | Stop a non-terminal job; already-fetched pages stay billed and readable. |
| list | The account's recent crawl jobs (limit ≤ 100 default 20, offset). |