
Capmonster Mcp Patchright Captcha Solver
io.github.CapMonsterCloudPublished by GitHub account CapMonsterCloudv1.1.3Updated Oct 24, 2026
Browser automation MCP for solving captchas with CapMonster Cloud via Patchright.
The publisher's own server: captcha.cc Human Verification
Overview
Stealth browser automation MCP server with 66 tools for navigating pages, extracting content, and managing sessions, cookies, and profiles.
- What you can do
- Provides a full browser automation surface over MCP: launching a stealth Chromium, navigating, clicking, filling forms, taking screenshots, exporting PDFs, and recording video. It exposes accessibility snapshots for LLM-friendly page control, network request tracking and interception, iframe actions, and granular cookie, localStorage, and sessionStorage management. It also supports authenticated API requests that reuse session cookies, persistent Chrome profiles, CDP attach to an already-running Chrome, and virtual WebAuthn passkeys.
- When to use it
- Use it when an assistant needs to drive a real browser for tasks such as filling forms, scraping rendered pages, capturing screenshots or PDFs, or testing web flows. It is also suited to workflows that need persistent logins, session import/export, or network interception.
- Requirements
- Runs locally as an npm package (capmonster-mcp-patchright) over stdio, or via SSE or Streamable HTTP. Requires Node.js and a matching Chromium build installed through patchright. Desktop only; no web executable. HTTP mode requires an owner identifier via a query parameter or the X-Browser-Owner header. No API keys or environment variables are declared.
Installation
In SourceWeft
- Open Capmonster Mcp Patchright Captcha Solver in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
capmonster-mcp-patchright: Stealth Browser MCP Server for AI Agents
Building an AI agent that has to work on anti-bot protected sites? Pair this stealth browser with the CapMonster Cloud MCP server, a cost-effective capsolver alternative and 2captcha alternative: reCAPTCHA v3 starts at $0.90 per 1,000 solves, which is up to 38% cheaper than 2Captcha and 10% cheaper than Capsolver. See the pairing example and the comparison below.
[License: MIT] [MCP Protocol] [npm]
Stealth browser MCP server for AI agents — 66 tools, Patchright-powered, reduced CDP automation signals.
Built for automation on sites protected by Cloudflare, Akamai, Kasada and DataDome.
When the page shows a CAPTCHA, pair it with the
CapMonster Cloud MCP server:
this server drives the browser, CapMonster Cloud solves the CAPTCHA. Use the 66 browser_* tools for AI-agent web scraping and browser automation with Claude, GPT and other MCP clients, powered by Patchright, a patched Playwright with reduced automation signals.
Learn more
👉 Get your CapMonster Cloud API Key
Fork of mcp-patchright that adds a per-call
world: "main" option to browser_evaluate / browser_run_code_unsafe, so page-defined window
globals are visible and callable. Defaults to Patchright's isolated stealth world (matching
upstream); opt into main only when a page's own script needs to see or be called by your
evaluated code. Everything else matches upstream mcp-patchright.
Why Patchright, not Playwright?
See the full comparison for details.
Quick start
With Claude / GPT / agents
🔗 Pair with CapMonster Cloud MCP for captcha solving
This server drives the browser; the CapMonster Cloud MCP server solves the CAPTCHA and the agent injects the token back into the page. Add both servers to your MCP client config:
Get your key from the CapMonster Cloud Dashboard.
Captcha solving MCP servers compared
Disclaimer: CapSolver and 2Captcha are trademarks of their respective owners. CapMonster Cloud is not affiliated with these entities. MCP coverage of other services is based on their publicly available documentation and repositories as of 27.10.2026 and may change. Pricing comparisons are based on publicly available data and internal benchmarking conducted on 27.09.2026.
Features
- 66 MCP tools — full browser automation surface
world: "main"opt-in —browser_evaluate/browser_run_code_unsafecan run in the page's real world to see/call page-defined globals (default stays isolated/stealth)browser_find— search the current aria snapshot for text/regex, cheaper than a fullbrowser_snapshotbrowser_save_blob— save a Blob/data URL produced by page code to disk- 3 transports — stdio, SSE, Streamable HTTP (
/mcp) - Persistent profiles — real Chrome profile, reuse across sessions
- Multi-page — tab management (new, list, switch, close)
- Owner-scoped HTTP sessions — isolate tabs per caller with
ownerquery/header - CDP attach — control an already-running Chrome
- Network tracking + interception — request list/detail, offline toggle, block/mock routes
- Session import/export —
browser_storage_save/browser_storage_load(cookies + localStorage) - Granular storage — per-key cookie / localStorage / sessionStorage CRUD (
browser_cookie_*,browser_localstorage_*,browser_sessionstorage_*) - Authenticated API requests —
browser_api_requestreuses session cookies (hybrid scraping) - Text/HTML extraction —
browser_get_visible_text/_html(token-light) - Iframe-aware — pass
frameSelectorto any element tool (click/fill/type/hover/press/wait_for/select/drag) to act inside an iframe - PDF export —
browser_save_pdfvia CDP (works in headed/stealth mode) - Video recording —
browser_startwithrecordVideo,browser_video_save; .webm flushed onbrowser_close - Element highlight —
browser_highlight/browser_hide_highlightoverlays for screenshots & recordings - Stealth profiles — proxy / geolocation / locale / timezone / colorScheme
- Console capture — real-time console message stream
- Fingerprint check —
browser_fingerprint_checkdiagnostics - Virtual passkeys — create, import, list, and delete WebAuthn credentials with private keys redacted by default
Tools
Full comparison HTML in /docs/tool-comparison.html.
browser_startbrowser_statusbrowser_navigatebrowser_new_pagebrowser_pagesbrowser_switch_pagebrowser_close_pagebrowser_snapshotbrowser_findbrowser_take_screenshotbrowser_clickbrowser_fillbrowser_typebrowser_hoverbrowser_press_keybrowser_wait_forbrowser_evaluatebrowser_fingerprint_checkbrowser_navigate_backbrowser_select_optionbrowser_handle_dialogbrowser_file_uploadbrowser_network_requestsbrowser_network_requestbrowser_console_messagesbrowser_resizebrowser_dragbrowser_fill_formbrowser_run_code_unsafebrowser_add_init_scriptbrowser_network_state_setbrowser_api_requestbrowser_get_visible_textbrowser_get_visible_htmlbrowser_iframe_clickbrowser_iframe_fillbrowser_route_blockbrowser_route_mockbrowser_route_clearbrowser_storage_savebrowser_storage_loadbrowser_cookie_listbrowser_cookie_getbrowser_cookie_setbrowser_cookie_deletebrowser_cookie_clearbrowser_localstorage_listbrowser_localstorage_getbrowser_localstorage_setbrowser_localstorage_deletebrowser_localstorage_clearbrowser_sessionstorage_listbrowser_sessionstorage_getbrowser_sessionstorage_setbrowser_sessionstorage_deletebrowser_sessionstorage_clearbrowser_passkey_installbrowser_passkey_createbrowser_passkey_listbrowser_passkey_deletebrowser_video_savebrowser_highlightbrowser_hide_highlightbrowser_save_blobbrowser_save_pdfbrowser_close
Development
Owner-scoped HTTP sessions
HTTP mode requires a stable owner on
the MCP URL (?owner=<id>) or with the X-Browser-Owner header. Page listing,
switching, navigation, and closing are restricted to that owner's tabs. Delete
/owners?owner=<id> to close all tabs owned by one caller without stopping the
browser or clearing the profile.
Release
Install the matching Chromium build once, then prepare a release from the exact
dependency versions in package-lock.json, run the full verification suite,
and inspect the package without publishing it:
By default, browser_start launches Chromium via patchright as headed real Chrome with a persistent profile at:
You can override it with the userDataDir tool argument or STEALTH_PLAYWRIGHT_USER_DATA_DIR.
To attach to an already-running Chrome instead of launching one, start Chrome with remote debugging and pass cdpEndpoint to browser_start:
browser_snapshot returns Playwright's AI aria snapshot. Use [ref=eN] values from that snapshot with browser_click, browser_fill, browser_type, browser_hover, browser_press, and browser_wait_for by passing { "ref": "eN" }. CSS selectors remain supported via { "selector": "..." }.
MCP config example:
Direction
Shipped:
- ✅ persistent user data dirs
- ✅ CDP attach to real Chrome
- ✅ proxy / timezone / locale / geolocation profiles
- ✅ accessibility snapshots for LLM-friendly page control
- ✅ fingerprint diagnostics
- ✅ network interception (block / mock)
- ✅ session import/export (storageState)
- ✅ PDF export
- ✅ authenticated API requests (reuse browser cookies)
- ✅ lightweight text/HTML extraction
- ✅ iframe actions
- ✅
world: "main"opt-in forbrowser_evaluate/browser_run_code_unsafe - ✅ aria-snapshot search (
browser_find) - ✅ save Blob/data URL output to disk (
browser_save_blob)
Next:
- rebrowser-playwright backend
- codegen sessions
- coordinate-based (vision) clicks
- tracing / video recording
❓ FAQ
What is capmonster-mcp-patchright? A stealth browser MCP server for AI agents with 66 tools, built on Patchright, a patched Playwright with reduced CDP automation signals.
Does it solve CAPTCHAs? No. This server drives the browser. Pair it with the CapMonster Cloud MCP server to solve reCAPTCHA, Cloudflare Turnstile, DataDome and other captchas.
Is CapMonster Cloud a capsolver alternative or a 2captcha alternative for AI agents?
For the captcha solving part, yes. The CapMonster Cloud MCP server covers more captcha types than the CapSolver MCP server (reCAPTCHA v2, v3 and Turnstile) and the 2Captcha mcp-captcha-solver project (reCAPTCHA v2), and reCAPTCHA v3 starts at $0.90 per 1,000 solves. See the comparison above and its disclaimer.
How is it different from Playwright?
Patchright removes the Runtime.enable and Console.enable calls and the --enable-automation flag, and navigator.webdriver is not true. See the comparison table above.
Can it control an already-running Chrome?
Yes. Start Chrome with remote debugging and pass cdpEndpoint to browser_start.
⚖️ Responsible use
Use this server only on websites you own or have permission to automate, and in line with the terms of service of those websites and applicable law. Patchright reduces common automation signals; acceptance of automated traffic by any site is not guaranteed.
📚 Related
- CapMonster Cloud MCP Server — the CAPTCHA-solving part of the workflow
- CapMonster Cloud MCP page
- CapMonster Cloud Documentation
- Model Context Protocol (MCP) Docs
📄 License
Source: README.md at commit 9949035
Tools
0Version history
1- v1.1.3LatestSep 18, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Captcha integrations

captcha.cc Human Verification
cc.captchaOfficial publisher
A remote MCP server for captcha.cc that helps an assistant generate CAPTCHA integration snippets and create live challenges for testing.

CaptchaNo
Published by GitHub account DishantSinghDev2
CaptchaNo MCP server lets an AI agent solve reCAPTCHA v2/v3/Enterprise, Turnstile, DataDome and image captchas through a paid solving service.

rea-captcha
Published by GitHub account masakaai
A local stdio MCP server that detects CAPTCHA challenges in an agent's existing browser session and coordinates authorized completion or human handoff before a

Capmonster Mcp Captcha Solver
Published by GitHub account CapMonsterCloud
Lets an AI agent submit CAPTCHA-solving tasks to CapMonster Cloud and poll for results, covering reCAPTCHA, Turnstile and other anti-bot challenges.

Captcha Mcp
Published by GitHub account zekebuilds-lab
A local MCP server that issues proof-of-work or Lightning-paid challenges so an assistant can obtain short-lived access tokens from a PowForge captcha backend.