MCP App Store
by KeenEthics
String icon

String MCP Server for ChatGPT

By String

Overview

String turns the public web into LLM-ready data for AI agents. Search the web, read any public page as clean Markdown, and map a site's pages, so ChatGPT and Codex answer from live sources with links you can check.

How to connect

  1. ChatGPT: Open the String listing in the ChatGPT app directory and choose Connect. ChatGPT listing String exposes 6 tools here.

Tools

web_access_fetch

ChatGPT
Fetch a caller-specified HTTP(S) URL and get clean, LLM-ready Markdown back. Primary use (the common case): pass only a url. The page is fetched with a normal GET and returned as Markdown — no other parameters are needed. ``json { "url": "https://example.com/article" } ` **Best for:** any public URL, including pages that render their content client-side (news, docs, blogs, web apps). **Not for:** searching the web when you don't have a URL — use web_access_search instead. **Optional parameters (omit unless you need them):** - format — markdown (default), raw (the destination's verbatim body), or json (a { statusCode, headers, data } envelope with the destination's status and headers). - executeJS — set true to render JavaScript for SPAs when the content comes back empty. - headers — forward custom request headers; not combinable with executeJS, which runs in a browser. - countryCode — ISO 3166-1 alpha-2 (e.g. "US") to get the page as it is served in that country. - solveCaptcha — defaults false, so a challenge page fails fast and is reported as an error; set true to have the request attempt the challenge. **To send a direct POST, PUT or PATCH** (with a body), use web_access_request — this tool only issues GETs. Plenty of those calls are reads: a GraphQL query, a search backend that takes a body, a JSON API that refuses GET. **Returns:** Markdown by default; the verbatim body or a JSON envelope when format` is set accordingly. Requests must comply with destination policy, robots directives, rate limits, and access controls. Challenge handling is subject to the caller's String account and organization policy.

web_access_request

ChatGPT
Send a POST, PUT or PATCH request to any URL, through String's Web Access API. It works like web_access_fetch, but for calls that submit data rather than read a page — a JSON API that only accepts POST, a GraphQL endpoint, a search backend that takes a body. Use web_access_fetch instead whenever you only need to read a page. This tool sends a body to the destination rather than reading it, so use it only for a request the user actually asked for. Usage Example: ``json { "url": "https://api.example.com/search", "method": "POST", "body": { "q": "widgets" } } `` Returns: The destination's response, in the requested format.

web_access_sitemap_quote

ChatGPT
Quote an asynchronous crawl of authorized public pages on one website. Nothing is crawled or billed: the quote creates a job that waits for approval. Starting from one URL, the crawler follows same-domain links breadth-first and can also seed from the site's /sitemap.xml. Requests must comply with destination policy, robots directives, rate limits, and access controls. Use it to discover pages for site audits, authorized retrieval worklists, or coverage checks before fetching individual pages. Not for: reading one page's content (use web_access_fetch) or open-ended web queries (use web_access_search). Requires url. Optional: maxPages (1–10000, default 10), maxDepth (1–100, default 2), pathPrefix (only crawl URLs whose path starts with this, e.g. "/docs"), budgetUsd (spend ceiling; the crawl stops with status token_cap_exceeded if it would exceed it), useSitemap (also seed the site's root /sitemap.xml — one extra billed page, but finds pages links miss). A maxPages or maxDepth outside its range, 0 included, is rejected rather than replaced by the default — omit the field to get the default. ``json { "url": "https://example.com", "maxPages": 200, "maxDepth": 3 } ` **Returns:** jobId, estimatedPages, and estimatedCostUsd, with status awaiting_approval. A 403 means the target domain is blocked for this account (contact support@usestring.ai). **Next:** show the user estimatedCostUsd. Only once they approve that cost, call web_access_sitemap_start with the jobId`.

web_access_sitemap_start

ChatGPT
Start a crawl that web_access_sitemap_quote quoted. This is the billing-consent step: pages are billed as they are fetched, capped by the quote or budgetUsd. Call it only after the user has approved the quote's estimatedCostUsd. Requires jobId. Fails with status 402 if the account balance cannot cover the quote; a 409 partial_state error means an earlier start was interrupted — just call this tool again. A 404 means the job doesn't exist or belongs to another account. Returns: the jobId and its new status. Next: poll web_access_sitemap_status until the job is terminal; the terminal response carries its URLs.

web_access_sitemap_status

ChatGPT
Poll a crawl job until it is terminal; the terminal response also carries the URLs it discovered. Statuses: awaiting_approval → running → terminal completed | failed | canceled | token_cap_exceeded (budget hit before maxPages; collected results are still readable). While running it returns pending and processed counts and no URLs; a partial_state status means an interrupted start — call web_access_sitemap_start again to repair it. Poll every few seconds for small crawls; give hundreds-of-pages crawls tens of seconds between polls. Once the job is terminal, the response carries total and urls, one page of the discovered URLs. Optional limit (1–5000, default 1000) and offset (≥ 0) choose the page; out-of-range values are rejected. Each entry has url, statusCode (0 = discovered but not fetched), depth, parentUrl, isSitemap, sourceType, and an error when that page failed. discoveredUrls (links found on the page) is only present for ~1h after completion; afterwards results come from durable storage which omits it — everything else stays available. Requires jobId. A 404 means the job doesn't exist or belongs to another account. If the job is terminal but its URLs cannot be read, the call fails rather than return the status without them; call it again. Returns: the jobId and status, with pending, processed, pagesProcessed, estimatedCostUsd, errorMessage and finishedAt as the job reports them, and total and urls once it is terminal. Next: call again with offset advanced by the page size until it reaches total; read a page's content with web_access_fetch.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/string"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/string)