[!IMPORTANT] The official 2Captcha MCP package is @2captcha/mcp (published under the @2captcha npm organization). The unscoped 2captcha-mcp package on npm is not affiliated with 2Captcha — don't put…
2captcha-mcp is an MCP project maintained in the 2captcha/2captcha-mcp repository. The maintainer describes its purpose as “[!IMPORTANT] The official 2Captcha MCP package is @2captcha/mcp (published under the @2captcha npm organization). The unscoped 2captcha-mcp package on npm is not affiliated with 2Captcha…”. Read the project documentation for the complete scope.
The documented npm package is @2captcha/mcp. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
The example declares API_TOKEN. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-13.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| Group | Tools |
| parsing | scrape_page, search_web, discover_urls, discover_search_params, parse_marketplace, extract, get_account |
| batch | scrape_pages, parse_pages, get_job, cancel_job |
| captcha | list_captcha_types, solve_captcha, detect_captcha, solve_captcha_on_page, captcha_report, captcha_balance |
| browser | 11 browser_ tools |
| browser_full | all 23 browser_ tools |
| all | everything the server advertises |
| scrape_page | Fetch a page and return its readable content as markdown (or raw HTML with clean=false). Options: render, keep_links, structured_data, country… |
| search_web | Find URLs for a query: ranked organic results with title, url and snippet. Options: count, country, engine. |
| discover_urls | List the URLs a site publishes in robots.txt and XML sitemaps — a reviewable inventory for scrape_pages/parse_pages, with pattern/prefix filters. Not a crawler. |
| discover_search_params | A site's real URL search parameters, read off one page: the query parameters its own links use (with values known to work) plus any controls. Use it instead… |
| parse_marketplace | Product page (target="product") or listing (target="search_results") → structured JSON. Pass schema for your own shape, include_offers for Amazon Buy-Box… |
| extract | Any URL or raw text + your JSON Schema → extracted JSON. instructions steers the extraction. |
| get_account | Tenant identity, configured capabilities, session spend counters. |
| get_job | Poll status and collect per-item results. |
| cancel_job | Stop a running job (stops the spending). |
| Category | Tools |
| Read | browser_snapshot (accessibility tree with element refs), browser_get_text, browser_get_html |
| Sessions | browser_save_session, browser_load_session, browser_list_sessions |
| list_captcha_types | The catalogue of solvable types with their required parameters — call it before solve_captcha instead of guessing. |
| solve_captcha | Solve a CAPTCHA of any supported kind; returns the token/answer, a captcha_id, and the cost. |
| detect_captcha | Identify the wall on a page — widget type, sitekey, whether a solvable task can be built from it, and the exact solve_captcha call to issue. Pass html from… |
| solve_captcha_on_page | Detect + solve in one step, and return an apply block: a self-contained JS expression to evaluate, or a cookie to add and a URL to re-request. |
| captcha_report | Report a solution good/bad (bad reports refund). |
| captcha_balance | Current balance in USD. |
| session_stats | Tool usage during this session (calls per tool, rate-limit window). Handled locally, free. |
{
"mcpServers": {
"2captcha": {
"command": "npx",
"args": [
"@2captcha/mcp"
],
"env": {
"API_TOKEN": "YOUR_API_TOKEN"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| API_TOKEN | Declared in the maintainer’s client configuration. | Yes |
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
MCP stdio server for fetching Confluence Wiki pages with managed browser authentication.
Fast browser automation MCP server for LLMs — persistent Chromium, ref-based interaction, cookie migration
Find the free ImgVX AI browser tool for any image job: remove backgrounds, upscale, compress.
Your browser will open for authorization on first use.