Integrations

MCP Server

title: MCP Server subtitle: Connect AI assistants to browser automation via Model Context Protocol slug: integrations/mcp

The Skyvern MCP server lets AI assistants like Claude Desktop, Claude Code, Codex, Cursor, and Windsurf control a browser. Your AI can fill out forms, extract data, download files, and run multi-step workflows, all through natural language.

What you can do

The MCP server exposes 33 tools across 6 categories:

CategoryKey toolsWhat they do
Browser session managementskyvern_browser_session_create, skyvern_browser_session_close, skyvern_browser_session_list, skyvern_browser_session_connectOpen, manage, and reuse browser sessions
Browser actionsskyvern_act, skyvern_navigate, skyvern_click, skyvern_type, skyvern_scroll, skyvern_select_option, skyvern_press_key, skyvern_waitControl the browser with natural language or CSS/XPath selectors
Data extractionskyvern_extract, skyvern_screenshot, skyvern_evaluatePull structured data from pages, capture screenshots, run JavaScript
Validationskyvern_validateCheck page conditions using AI (returns true/false)
Credentialsskyvern_credential_list, skyvern_credential_get, skyvern_credential_deleteLook up stored credentials for login flows
Workflowsskyvern_workflow_create, skyvern_workflow_run, skyvern_workflow_status, skyvern_workflow_get, skyvern_workflow_update, skyvern_workflow_deleteBuild and execute multi-step automations

Your AI assistant decides which tools to call based on your instructions. For example, asking “go to Hacker News and get the top post title” triggers skyvern_browser_session_create, skyvern_navigate, skyvern_extract, and skyvern_browser_session_close automatically.

Which setup should I use?

Cloud setup (recommended)Local mode
Best forMost users — Skyvern Cloud handles everythingSelf-hosting Skyvern with your own infrastructure
Install requiredNonePython 3.11+ and pip install skyvern
How it connectsYour AI client connects to Skyvern Cloud over HTTPSA local Python process runs on your machine
API keyFrom app.skyvern.comFrom your self-hosted Skyvern instance

If you have a Skyvern Cloud account, use the cloud setup below. It takes 30 seconds and works immediately.

Quick start

Get your API key from Settings in the Skyvern dashboard, then pick your client below.

$claude mcp add-json skyvern '{"type":"http","url":"https://api.skyvern.com/mcp/","headers":{"x-api-key":"YOUR_SKYVERN_API_KEY"}}' --scope user

That’s it — no Python, no pip install, no local server. Your AI assistant connects directly to Skyvern Cloud over HTTPS.

Alternative: Local mode (self-hosted)

Use this if you are self-hosting Skyvern and want the MCP server to talk to your own instance instead of Skyvern Cloud. This runs a lightweight Python process on your machine that connects to your local Skyvern server.

Supported Python Versions

Local mode requires Python 3.11, 3.12, or 3.13.

$pip install skyvern

Before using MCP, start your local Skyvern server:

$skyvern run server

Then configure your AI client to use stdio transport:

$# For Skyvern Cloud, use https://api.skyvern.com instead of localhost
$claude mcp add --transport stdio skyvern \
>  --env SKYVERN_BASE_URL=http://localhost:8000 \
>  --env SKYVERN_API_KEY=YOUR_SKYVERN_API_KEY \
>  -- python3 -m skyvern run mcp

You can also run skyvern init to auto-detect installed clients and write configs automatically.

ClientFormatPath
Claude Desktop (macOS)JSON~/Library/Application Support/Claude/claude_desktop_config.json
Claude Desktop (Linux)JSON~/.config/Claude/claude_desktop_config.json
Claude Code (project)JSON.mcp.json in project root
Claude Code (global)JSON~/.claude.json
Codex (global)TOML~/.codex/config.toml
Codex (project)TOML.codex/config.toml in trusted project
CursorJSON~/.cursor/mcp.json
WindsurfJSON~/.codeium/windsurf/mcp_config.json

See it in action

Claude Desktop looking up the top Hacker News posts:

Cursor finding programming jobs:

Windsurf searching Form 5500 and downloading files:

Troubleshooting

Double-check that your API key is correct. You can find or regenerate it at Settings. Make sure there are no extra spaces or newlines when pasting the key.

If you recently regenerated your API key, update it in your MCP config and restart your AI client.

Skyvern browser sessions take a few seconds to start. If a tool call times out, try again — the first call in a new session is slower than subsequent ones.

If timeouts persist, check that your Skyvern account is active and has available credits at app.skyvern.com.

The Skyvern MCP server requires Python 3.11, 3.12, or 3.13. Check your version with python3 --version. If you have multiple Python versions installed, make sure the command in your MCP config points to a supported version:

$which python3.11
$# Use this path in your MCP config

You can also use pipx to install in an isolated environment:

$pipx install skyvern

Make sure the Skyvern server is running before using MCP tools:

$skyvern run server

Confirm the server is reachable at http://localhost:8000. If you changed the port, update SKYVERN_BASE_URL in your MCP config to match.

Verify that the command path in your MCP config is correct:

$which python3

Use the full absolute path (e.g., /usr/bin/python3 or /Users/you/.pyenv/shims/python3), not just python3. Restart your MCP client after editing the config file.