500 free credits · 1 credit per successful fetch · Open-source MCP server
Server URL
https://mcp.unblockingapi.com/mcpThe app never sees your API key. Disconnect it any time under Connected apps.
Our proxy network (residential and mobile connections where a site needs them) and a real browser get Claude past CAPTCHAs, bot walls and geo-blocks that stop its own fetch.
Where a template covers a site - Google, property portals, company registries - Claude gets named fields, not markup.
One connector for Claude.ai and Claude Desktop, and a plugin for Claude Code. Sign in once, no key to copy.
Claude's own web fetch stalls on anything that renders with JavaScript or sits behind bot protection - a product page that loads prices client-side, a search page with a CAPTCHA, a portal that only answers from its own country. UnblockingAPI fetches through our proxy network (residential and mobile connections where a site needs them) and switches to a real browser when a site needs one, learning per site which it takes.
The hosted server at https://mcp.unblockingapi.com/mcp does the rest: Claude signs in with your UnblockingAPI account, so there is no key to copy and nothing to install, and it never sees your key.
Paste the hosted URL and approve access. No key to copy, nothing to install.
UnblockingAPI and paste https://mcp.unblockingapi.com/mcp.Same hosted URL, authenticated by your key in a header.
claude mcp add --transport http unblockingapi https://mcp.unblockingapi.com/mcp \
--header "Authorization: Bearer your_api_key_here"Prefer to run the server yourself? It is open source and runs with npx (Node.js 18+).
claude mcp add with the package and your key.claude mcp add unblockingapi \
-e UNBLOCKINGAPI_KEY=your_api_key_here \
-- npx -y @unblockingapi/mcpClaude Desktop: add this to claude_desktop_config.json (Settings → Developer → Edit Config), then restart the app.
{
"mcpServers": {
"unblockingapi": {
"command": "npx",
"args": ["-y", "@unblockingapi/mcp"],
"env": { "UNBLOCKINGAPI_KEY": "your_api_key_here" }
}
}
}/plugin marketplace add unblockingapi/mcp
/plugin install unblockingapi@unblockingapi-pluginsThen sign in: run /mcp, pick unblockingapi and choose Authenticate. A browser opens on your account; approve and you are done. New to this? Run /unblockingapi:setup and Claude walks you through it and confirms when it works. Check with /mcp: unblockingapi shows as connected with three tools.
Full guide with troubleshooting in the repository.
unblock skill points Claude at unblock_fetch for reading pages.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.Custom connectors work on Claude.ai, Claude Desktop and Cowork on every plan; the free plan allows one custom connector. On Team and Enterprise an owner adds it under Organization settings → Connectors, and members then click Connect to sign in.
It is the same hosted server, signed in with your account, plus four skills and a /unblockingapi:setup command that checks everything works. unblock teaches Claude the fetch-then-template workflow for reading pages; build-app, templates and app-recipes help it write code on the REST API, such as a rank tracker, price monitor or listings aggregator. With the server alone you get the same three tools without the skills.
Claude.ai has built-in Web search and fetch. Turn Web search off in the chat's tools menu, or say "use UnblockingAPI", and Claude reads pages with unblock_fetch. UnblockingAPI has no search tool of its own: for Google results it uses the kjellberg/google-search template.
No. Claude gets the page as Markdown and picks out what you asked for.
Not when you sign in. Claude 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 Claude'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 Claude 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.
One account, every assistant. Connect as many as you like, or see them all.