usestring/string-ai-mcp — explained in plain English
Analysis updated 2026-05-18
Let an AI coding assistant fetch webpages that are normally blocked by anti-bot protection or CAPTCHAs.
Give an AI assistant the ability to run web searches without hitting search engine rate limits.
Crawl an entire website and get back a mapped list of its URLs as a background job.
Connect String AI's Web Access API to VS Code, Cursor, Windsurf, or Claude Desktop with a short config snippet.
| usestring/string-ai-mcp | 00kaku/gallery-slider-block | 3rd-eden/ircb.io | |
|---|---|---|---|
| Stars | 0 | — | — |
| Language | JavaScript | JavaScript | JavaScript |
| Last pushed | — | 2021-05-19 | 2016-11-16 |
| Maintenance | — | Dormant | Dormant |
| Setup difficulty | easy | easy | easy |
| Complexity | 2/5 | 2/5 | 2/5 |
| Audience | developer | general | developer |
Figures from each repo's GitHub metadata at analysis time.
Requires a String AI API key, can be run instantly with npx or installed globally with npm.
This project is the official Model Context Protocol server for String AI's Web Access API. The Model Context Protocol, or MCP, is a standard way for AI assistants like Claude Desktop, or code editors like VS Code, Cursor, and Windsurf, to connect to outside tools. This server acts as the bridge between those assistants and String AI's paid web access service, which is built to fetch web pages while getting around anti bot protection, CAPTCHAs, and pages that need JavaScript to render, and to run web searches that avoid rate limits and blocking on search engines. It exposes three tools to a connected AI assistant. One fetches a single webpage. Another runs a web search. The third crawls an entire website and maps out its URLs as a background job, following a quote, approve, poll, and read process, so nothing is actually crawled or billed until you explicitly approve the estimated cost first. Running it requires a String AI API key, which you set as an environment variable. You can run it directly with npx without installing anything permanently, install it globally as a command line tool, or build it yourself from the source code with npm. The README gives copy and paste configuration snippets for adding this server to VS Code, Cursor, Windsurf, and Claude Desktop, and mentions the MCP Inspector tool for testing the server's tools interactively in a browser before connecting it to a real assistant. Communication between the AI assistant and this server happens over standard input and output as the assistant spawns it as a child process, this server then forwards requests over HTTPS to String AI's actual API. The project is released under the MIT license.
An MCP server that connects AI assistants like Claude Desktop or Cursor to String AI's paid web fetching, searching, and site-crawling API.
Mainly JavaScript. The stack also includes JavaScript, Node.js, MCP.
Use freely for any purpose, including commercial use, as long as you keep the copyright notice.
Setup difficulty is rated easy, with roughly 5min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.