orchords-web-pilot
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PILOT_HEADLESS | No | Set to 'false' to watch the agent work. Controls whether the local browser runs headless. | true |
| PILOT_HTTP_HOST | No | The host the HTTP transport binds to. HTTP transport only. | 127.0.0.1 |
| PILOT_HTTP_PATH | No | The path for the HTTP transport endpoint. HTTP transport only. | /mcp |
| PILOT_HTTP_PORT | No | The port the HTTP transport listens on. HTTP transport only. | 8788 |
| PILOT_TRANSPORT | No | The transport to use. 'stdio' for desktop agents, 'http' for hosted/shared. | stdio |
| BROWSER_WS_ENDPOINT | No | WebSocket endpoint of a remote browser (e.g., Browserless, hosted Chrome, own grid). If set, the server connects to this instead of launching a local browser. | |
| PILOT_CAPTCHA_SOLVER_URL | No | Endpoint for an external captcha-solving service. Used by the captcha solver tool. | |
| PILOT_CAPTCHA_SOLVER_TOKEN | No | Bearer token for the captcha-solving service. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateC | Open a URL in the browser. |
| browser_snapshotA | Return the AI-oriented accessibility snapshot for the current page. Each node carries a |
| browser_clickB | Click an element identified by a snapshot ref, CSS selector, or x+y coordinates. Prefer |
| browser_typeB | Type text into the focused, matched, or ref-targeted element. |
| browser_fillC | Replace an input value via Playwright's fill() — accepts a selector or a snapshot ref. |
| browser_pressA | Press a non-text key (Enter, Tab, Escape, arrows, etc.). |
| browser_hoverB | Hover an element. Accepts a snapshot ref or a selector. |
| browser_dragC | Drag from one element to another. Accepts snapshot refs or selectors. |
| browser_selectB | Select an by value or label. Accepts a snapshot ref or a selector. |
| browser_screenshotB | Capture a PNG screenshot. Returns base64 or saves to disk if savePath is set. |
| browser_evaluateB | Run a JS expression in the page context and return its JSON-serializable result. |
| browser_waitB | Wait for a selector/text or a fixed duration. |
| browser_consoleB | Read console messages captured for the current session. |
| browser_networkB | List network requests captured for the current session. |
| browser_captcha_solveB | Forward a captcha challenge to the configured solver (PILOT_CAPTCHA_SOLVER_URL). |
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 15 tools
Each browser_ tool serves a distinct, well-defined action—navigation, snapshot, click, type, fill, press, hover, drag, select, screenshot, evaluate, wait, console, network, and captcha solving. Even the text-entry tools (type vs. fill) are clearly differentiated by their descriptions, eliminating ambiguity.
All tools consistently use the 'browser_' prefix followed by a descriptive verb (or verb+noun) in lowercase snake_case, such as browser_navigate, browser_screenshot, browser_captcha_solve. This uniform pattern makes the tool names predictable and easy to learn.
With 15 tools, the set is appropriately scoped for a comprehensive browser automation server. Each tool covers a specific aspect of web interaction without being redundant or overwhelming, staying within the ideal range for a focused purpose.
The tool surface covers the full lifecycle of browser interactions: navigation, inspection, element actions, waiting, screenshotting, JavaScript execution, and special handling like captchas. Minor gaps like tab/multi-page management or dialog handling exist, but they are non-essential for most web-pilot tasks.