Skip to main content

Requirements

  • An MCP client such as Claude Desktop, Cursor, Codex, or your own MCP runner
  • For hosted Browser MCP: a StableBrowse API key from the settings page
  • For local Browser MCP: Node.js 20 or newer and a StableBrowse MCP checkout

Hosted Browser MCP

Hosted Browser MCP is the recommended setup for end users. The browser runs in StableBrowse cloud; your LLM app only needs the MCP endpoint and your StableBrowse API key.
  1. Sign in to StableBrowse.
  2. Open settings.
  3. Create an API key.
  4. Add the hosted Browser MCP endpoint to your MCP client:
  1. Send the API key as a bearer token.
The client should authenticate every MCP request with:
Your LLM key stays with your LLM app or model provider. The StableBrowse API key authenticates access to the hosted browser.

Local install

Hosted Browser MCP does not require a local browser process. If you want to run the MCP server yourself, use a source checkout:

Run over stdio

Most desktop MCP clients use stdio:
Example MCP client config:
Then ask the client something like:

Run as an HTTP endpoint

For local integration tests:
Endpoints: For a hosted deployment that accepts dashboard-created StableBrowse API keys:

Common options

Environment variables use the STABLEBROWSE_* prefix. For example:

First successful run

In a typical run the agent should:
  1. call create_session
  2. call navigate
  3. call content.get_markdown, extract.page_summary, or snapshot
  4. use click, fill, fill_form, or interact if action is needed
  5. return the final answer
If an agent takes screenshots for ordinary text tasks, improve its system prompt. Screenshots are useful for visual verification, but text and structured extraction tools are cheaper and usually more reliable.

Troubleshooting