Browser Automation MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MODEL_API_KEY | No | API key for the configured model provider (works with any provider) | |
| GEMINI_API_KEY | No | Alternative to MODEL_API_KEY for Gemini (the default model) | |
| OPENAI_API_KEY | No | Only needed for stagehand_demo_video (TTS via gpt-4o-mini-tts) | |
| NGROK_AUTHTOKEN | No | Only needed for cloud: true with localhost URLs | |
| BROWSERBASE_API_KEY | No | Only needed for cloud: true | |
| STAGEHAND_VARIABLES | No | Optional JSON map of variables auto-injected into stagehand_act, stagehand_agent, and stagehand_scenario | |
| BROWSERBASE_PROJECT_ID | No | Only needed for cloud: true | |
| VERCEL_AUTOMATION_BYPASS_SECRET | No | Optional, for Vercel preview deployments |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"subscribe": true,
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| stagehand_session_createA | Create a browser session and set it as active. Uses local Playwright by default; set cloud=true for Browserbase cloud. |
| stagehand_session_closeA | Close the current browser session and reset the active context. |
| stagehand_navigateA | Navigate to a URL in the browser. Only use this tool with URLs you're confident will work and be up to date. Otherwise, use https://google.com as the starting point. Supports localhost URLs when using cloud browser - automatically tunnels via ngrok. |
| stagehand_actB | Perform a single action on the page (e.g., click, type). |
| stagehand_extractA | Extract structured data or text from the current page using an instruction. |
| stagehand_observeB | Find interactive elements on the page from an instruction; optionally return an action. |
| stagehand_screenshotA | Capture a full-page screenshot and return it (and save as a resource). |
| stagehand_get_urlA | Return the current page URL (full URL with query/fragment). |
| stagehand_agentB | Execute a task autonomously using Stagehand agent in hybrid mode. The agent uses both DOM-based and coordinate-based actions for maximum reliability. |
| stagehand_scenarioA | Execute a multi-step test scenario (arrange/act/assert) using the Stagehand agent. Returns structured pass/fail/blocked results per assert step. |
| stagehand_run_scriptA | Run a Stagehand script (default export from defineScript) against the
current browser session. Accepts either a file |
| stagehand_demo_videoA | Record a narrated demo video of a known-good Stagehand script. Each action runs through stagehand.act with a CDP screencast attached; per-action narration is generated via OpenAI TTS; per-segment mp4s are concatenated into a single final.mp4. Uses the active Stagehand session — make sure the page is at the desired starting state before calling. Requires OPENAI_API_KEY. |
| agent_browser_helpA | Show help for agent-browser, a low-level browser automation CLI for precise, deterministic control. Call this to see available commands. |
| agent_browser_runA | Run a low-level browser command. Use over Stagehand when you need precise, deterministic control — element-by-ref interactions, DOM inspection, network debugging, JS evaluation. Shares the same browser session as Stagehand. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Several tools overlap in purpose, particularly the multi-step execution tools (stagehand_agent, stagehand_scenario, stagehand_run_script, stagehand_demo_video) and the action/observation pair (stagehand_act, stagehand_observe). The descriptions do provide distinguishing details, but the boundaries are not immediately obvious.
Naming conventions are mixed: some tools use verb_noun (stagehand_session_create, stagehand_run_script), some use bare verbs (stagehand_navigate, stagehand_act), and some use nouns (stagehand_agent, stagehand_scenario). Additionally, there are two different prefixes (stagehand_ vs agent_browser_) without a consistent pattern across the whole set.
14 tools is on the higher end of the typical range. While each tool has a distinct function, the set includes several tools for running multi-step workflows (agent, scenario, run_script, demo_video) that could have been consolidated, making the count slightly over-scoped but still reasonable.
The tool set covers the full browser automation lifecycle: session management, navigation, interaction, extraction, screenshots, script execution, and low-level control. There are no obvious missing operations for the domain.