Is it really better than Playwright for messy pages?

On pages that change layout often, yes — Skyvern uses vision plus DOM signals so it survives minor structural shifts that break CSS selectors. On stable pages, Playwright is faster and cheaper.

How does it handle CAPTCHAs?

Skyvern detects CAPTCHAs and pauses the run, optionally handing off to a CAPTCHA-solving service if configured. It does not bypass them by itself.

Both. The OSS repo runs anywhere; Skyvern also offers a managed cloud version with the same MCP surface. Pick by ops appetite.

Skyvern

Name: Top MCPs — curated MCP directory
Creator: Top MCPs
License: https://creativecommons.org/licenses/by/4.0/

Open-source agentic browser automation that handles login walls and CAPTCHAs.

Score 78(?)Skyvern AIAGPL-3.0 22kVerified May 26, 2026Top MCPs for Browser Automation →

Install View on GitHub

Quick answer

What it does

Provides MCP tools to submit a Skyvern task (URL + goal + optional payload), poll status, and retrieve structured results. Skyvern itself runs the browser, handles selectors via vision, and recovers from minor page changes.

Best for

Login-walled flows
Resilient to layout changes
End-to-end automation under one tool call
Vision-driven selectors

Not for

High-throughput scraping
Latency-sensitive workflows

Setup recipe

Pick your client, then follow the three steps.

Install

claude_desktop_config.jsonjson

{
  "mcpServers": {
    "skyvern": {
      "command": "pip",
      "args": [
        "install",
        "skyvern",
        "&&",
        "skyvern",
        "run",
        "mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}

Paste under mcpServers. Fully quit and reopen Claude after editing.

CLI or .mcp.jsonshell

# export OPENAI_API_KEY=YOUR_API_KEY
claude mcp add skyvern -- pip install skyvern && skyvern run mcp

Run from your repo. Commit .mcp.json to share with your team.

.cursor/mcp.jsonjson

{
  "mcpServers": {
    "skyvern": {
      "command": "pip",
      "args": [
        "install",
        "skyvern",
        "&&",
        "skyvern",
        "run",
        "mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}

Global path: ~/.cursor/mcp.json. Reload window after editing.

.vscode/mcp.jsonjsonc

{
  "servers": {
    "skyvern": {
      "command": "pip",
      "args": [
        "install",
        "skyvern",
        "&&",
        "skyvern",
        "run",
        "mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}

VS Code uses the "servers" key (not "mcpServers").

~/.codeium/windsurf/mcp_config.jsonjson

{
  "mcpServers": {
    "skyvern": {
      "command": "pip",
      "args": [
        "install",
        "skyvern",
        "&&",
        "skyvern",
        "run",
        "mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}

Open via Cascade → hammer icon → Configure.

cline_mcp_settings.jsonjson

{
  "mcpServers": {
    "skyvern": {
      "command": "pip",
      "args": [
        "install",
        "skyvern",
        "&&",
        "skyvern",
        "run",
        "mcp"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}

Open via the Cline sidebar → MCP Servers → Edit.

~/.continue/config.jsonjson

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "pip",
          "args": [
            "install",
            "skyvern",
            "&&",
            "skyvern",
            "run",
            "mcp"
          ],
          "env": {
            "OPENAI_API_KEY": "${OPENAI_API_KEY}"
          }
        }
      }
    ]
  }
}

Continue uses modelContextProtocolServers with a transport block.

~/.codex/config.tomlshell

# ~/.codex/config.toml
[mcp_servers.skyvern]
command = "pip"
args = [
  "install",
  "skyvern",
  "&&",
  "skyvern",
  "run",
  "mcp",
]
env = { OPENAI_API_KEY = "${OPENAI_API_KEY}" }

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

~/.config/zed/settings.jsonjsonc

{
  "context_servers": {
    "skyvern": {
      "command": {
        "path": "pip",
        "args": [
          "install",
          "skyvern",
          "&&",
          "skyvern",
          "run",
          "mcp"
        ]
      },
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}

Zed calls them "context_servers". Settings live-reload on save.

ChatGPT → Apps directorynone

Skyvern doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

2
Set required secrets
Set OPENAI_API_KEY in your shell environment before launching your MCP client.
3
Try a minimum working prompt
Minimum working prompt pending verification. Try any prompt from the MCP’s README once installed.

Tools & permissions

Tools list pending verification. The server exposes tools over MCP; we haven’t yet parsed its capability manifest into this page. Check the GitHub repo for the authoritative list.

Security & scope

Access scope: Exec
Sandbox: Runs a real browser under the user (self-hosted) or in a Skyvern-managed container (cloud). Full network access.
Gotchas: AGPL license — using Skyvern as a hosted service triggers source-disclosure obligations.
Vision model calls are not free; long runs cost.
License-page assumptions: read the Skyvern terms before commercial use.

Agent prompt pack

— copy into Claude, Cursor, or ChatGPT.

Paste into Claude, Cursor, or ChatGPT. Edit the [brackets] before sending.

Recommend the best MCP servers for [task: e.g. browser automation work] in [client: Claude].

Constraints:
- Prefer tools that are [official | open-source | read-only] — pick what matters for my use case.
- Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport].
- Return at most 3 picks, ranked.

For each pick include:
1. One-sentence rationale.
2. The ready-to-paste install snippet for my client.
3. Any required secrets I need to create before installing.

Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-browser-automation

Compare Skyvern against a real alternative. Swap the second MCP in [brackets] if you want a different match.

Compare Skyvern MCP vs [Playwright MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"].

Judge them on:
- Setup time and complexity (what a new user hits first).
- Auth model (none / API key / OAuth 2.1) and credential risk.
- Transport (stdio / Streamable HTTP / SSE) and where the server runs.
- Required secrets and the blast radius if they leak.
- Operational risk in an unattended agent loop.
- Which one is "good enough" for a weekend prototype vs. production.

End with one sentence: which should I pick for my scenario, which is: [my scenario].

References:
- https://top-mcps.com/mcp/skyvern
- top-mcps.com listing for Playwright

Asks the agent to install and verify. Works inside Claude Code, Cursor Agent, Codex CLI.

Install the Skyvern MCP server for my [client: Claude] at the default config path for that client.

Use the exact install snippet published at https://top-mcps.com/mcp/skyvern (fetch https://top-mcps.com/mcp/skyvern.json for the canonical server.json if you can read URLs).

Before finishing:
1. Create the required secrets (OPENAI_API_KEY) and put them in the appropriate env block — do not hard-code them.
2. Restart or reload the client so it picks up the new server.
3. Verify the server is connected (green / running state) and at least one tool is listed.
4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry.

Confirm when done and list the tools the server now exposes.

Frequently asked questions

What changed

— 2 updates tracked.

May 26, 2026
Refreshed install snippets and fact sheet; verified for 2026.
Jan 20, 2025
Initial directory listing.

More Browser Automation MCPs

Other tools in the same category worth evaluating.

Puppeteer

Full browser automation: navigate, click, screenshot, and scrape.

browserautomationscrapingpuppeteer

5 minMedium

Playwright

Official

Official Microsoft browser automation across Chromium, Firefox, and WebKit.

browserautomationplaywrighttesting

5 minMedium

Browserbase

Official

Hosted, isolated Chromium runtime for AI agents that need a fresh browser per task.

browsercloudbrowserbaseautomation

5 minMedium

Compared with Skyvern

Side-by-side breakdowns for the choices people most often weigh against this MCP.

SkyvernvsPlaywright SkyvernvsBrowserbase SkyvernvsPuppeteer SkyvernvsAgentQL

Exploring Top MCPs for Browser Automation? See all Browser Automation MCPs →

Quick answer

What it does

Best for

Not for

Setup recipe

Install

Set required secrets

Try a minimum working prompt

Tools & permissions

Security & scope

Agent prompt pack

Full details

Frequently asked questions

Is it really better than Playwright for messy pages?

How does it handle CAPTCHAs?

Self-hosted or SaaS?

What changed

More Browser Automation MCPs

Puppeteer

Playwright

Browserbase

Compared with Skyvern