Cursor integration

Cursor's agent, with a browser of its own.

One click adds UnblockingAPI's hosted MCP server to Cursor; sign in and the agent reads live documentation, changelogs and pages that block automated tools - fully rendered, or as JSON where a template covers the site.

500 free credits  ·  1 credit per successful fetch  ·  Open-source MCP server

Cursor · hosted MCP server

Server URL

https://mcp.unblockingapi.com/mcp
  1. 1Click Add to Cursor, or add the URL to ~/.cursor/mcp.json
  2. 2Under Settings → MCP, click Login next to unblockingapi
  3. 3Sign in to UnblockingAPI and allow access

The app never sees your API key. Disconnect it any time under Connected apps.

Docs as they are today

Point the agent at a changelog or an API reference and it reads the live page instead of recalling an old version.

Real pages, fully rendered

Framework docs and dashboards that render client-side come back complete, not as an empty HTML shell.

Nothing to configure twice

Add it once to your global mcp.json and it's in every Cursor project you open.

Cursor's agent can fetch a page on its own, but it stalls on anything that renders with JavaScript or sits behind bot protection. UnblockingAPI gives it a real browser fetcher instead: a plain fetch first, a browser when the site needs one, learned per site.

If the agent needs fields rather than a page - a price, a title, a list of listings - find_templates finds a published template and unblock_fetch returns clean JSON.

Add it to Cursor

Hosted server: one click, then sign in

RecommendedSign in, no key

Paste the hosted URL and approve access. No key to copy, nothing to install.

  1. 1Add to Cursor
  2. 2Or put this in ~/.cursor/mcp.json:
{
  "mcpServers": {
    "unblockingapi": { "url": "https://mcp.unblockingapi.com/mcp" }
  }
}
Then open Settings → MCP, click Login next to unblockingapi, sign in to UnblockingAPI and allow access. The server turns green with three tools.

Hosted server with an API key

URL + API key

Same hosted URL, authenticated by your key in a header.

~/.cursor/mcp.json

{
  "mcpServers": {
    "unblockingapi": {
      "url": "https://mcp.unblockingapi.com/mcp",
      "headers": { "Authorization": "Bearer your_api_key_here" }
    }
  }
}
Use this if you'd rather not sign in, e.g. on a shared machine with a dedicated key.

Run it locally

Local server

Prefer to run the server yourself? It is open source and runs with npx (Node.js 18+).

  1. 1Add local server to Cursor then paste your key into the entry under Settings → MCP.

~/.cursor/mcp.json

{
  "mcpServers": {
    "unblockingapi": {
      "command": "npx",
      "args": ["-y", "@unblockingapi/mcp"],
      "env": { "UNBLOCKINGAPI_KEY": "your_api_key_here" }
    }
  }
}

Make it the agent's default

Cursor has a web tool of its own. One rule in .cursor/rules/unblockingapi.mdc makes the agent read every page through UnblockingAPI.
---
description: Read web pages through UnblockingAPI
alwaysApply: true
---

When you need the contents of a URL, use the `unblock_fetch` tool from the
unblockingapi MCP server instead of the built-in web tool. Leave render unset:
the API fetches plainly first and switches to a real browser when the site needs
one. Before parsing a recognisable site by hand, call `find_templates` with the
URL - if a template covers it, pass its reference as `unblock_fetch`'s template
argument to get structured JSON instead of HTML.

Try it in Cursor

Ask this once you're connected. Cursor should find the idealista template with find_templates and come back with parsed results instead of HTML.
Use unblockingapi to get the listings on https://www.idealista.com/venta-viviendas/estepona-malaga/ as structured data, then summarise the three cheapest.

Cursor questions

Into ~/.cursor/mcp.json for every project, or a project-local .cursor/mcp.json. You can see and toggle it under Settings → MCP.

Add the rule above to .cursor/rules/unblockingapi.mdc, or to your User Rules for every project. The agent then reaches for unblock_fetch whenever it needs a page.

For the hosted server, click Login next to it under Settings → MCP and allow access. For the local server, install Node.js 18+ and toggle the server off and on. An out-of-credits or wrong-key problem comes back as a clear message from the tool, not a silent failure.

Yes. UnblockingAPI runs a real browser and routes through our proxy network (residential and mobile connections where a site needs them), so the agent gets the rendered page even for single-page apps and sites that block plain HTTP requests. The full guide is in the repository.

Not when you sign in. Cursor gets an access token for the hosted server, and the server uses your key on its behalf, so the key itself never leaves UnblockingAPI. You can disconnect any time under Connected apps. If you connect with an API key header instead, the key is stored in Cursor's own config.

The MCP server is free and open source. Fetches run on your UnblockingAPI account: every successful fetch costs 1 credit and failed ones are free. New accounts get 500 free credits with no credit card, and bigger credit packs add bonus credits. Looking up templates is free.

Three, all read-only. unblock_fetch reads any URL through our proxy network (residential and mobile connections where a site needs them) and a real browser, picking a plain fetch or a browser per site by itself. It returns the page as Markdown (HTML on request), or JSON with a template. find_templates checks whether a published template covers a site. get_build_guide gives Cursor the API reference and app guides when you build an app on the API. Details on the MCP server page.

The hosted server: nothing to install or update, and most apps sign in without a key. Run it locally with npx -y @unblockingapi/mcp if you prefer to keep the process on your machine - the tools and costs are the same.

Give Cursor a real browser.

500 free credits, no credit card. Connect in under a minute.