About WebRun Browser Automation
Run multi-step tasks in a real Chrome browser: persistent environments, live view, human takeover
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
Endpoint
https://api.webrun.ai/mcpCopy install command
Claude CodeTerminal
claude mcp add --transport http ai-webrun-webrun https://api.webrun.ai/mcpCursor.cursor/mcp.json
{"mcpServers":{"ai-webrun-webrun":{"type":"http","url":"https://api.webrun.ai/mcp"}}}Open in CursorVS Code.vscode/mcp.json
{"servers":{"ai-webrun-webrun":{"type":"http","url":"https://api.webrun.ai/mcp"}}}Open in VS CodeClaude Desktopclaude_desktop_config.json
{"mcpServers":{"ai-webrun-webrun":{"type":"http","url":"https://api.webrun.ai/mcp"}}}Windsurf~/.codeium/windsurf/mcp_config.json
{"mcpServers":{"ai-webrun-webrun":{"serverUrl":"https://api.webrun.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
All endpoints
Streamable HTTP
https://api.webrun.ai/mcpAuth requiredTools
21| Parameter | Type | Required | Description |
|---|---|---|---|
| files | array | No | Optional file IDs to attach: ids returned by POST /files/upload, or any file already in one of the user's environment catalogs (GET /environments/:id/files). Max 5 files. |
| model | string | No | Optional model name or profile key (from global config). Falls back to the configured default. |
| proxy | object | No | Proxy configuration. WebRun-managed: { source: "WebRun", country: "GB" }. Custom: { source: "custom", type: "http"|"socks", host, port, username?, password? }. Omit for no proxy. Social/messaging automation (WhatsApp, Telegram, Instagram, Facebook, X, LinkedIn, TikTok): prefer country = the country the user is in right now — recommend it and confirm the country with them first; a mismatch is the usual cause of refused logins and sessions that log out repeatedly. |
| proxy.host | string | No | Custom proxy host |
| proxy.port | number | No | Custom proxy port |
| proxy.type | enum | No | Custom proxy typehttp | socks |
| proxy.level | enum | No | Proxy level. "chrome" (default) applies proxy via browser extension (instant, no swap). "system" launches Chrome with --proxy-server flag (requires instance swap).system | chrome |
| proxy.source | enum | No | Proxy providerWebRun | custom |
| proxy.country | string | No | ISO country code for WebRun proxy (e.g. "GB", "US") or "random" for a random country with good connectivity |
| proxy.password | string | No | Custom proxy password (optional) |
| proxy.username | string | No | Custom proxy username (optional) |
| debugC | boolean | No | Enable debug mode on the instance (default: false) |
| prompt | string | Yes | Task description in natural language |
| secrets | array | No | Domain-matched secrets [{match, fields}] passed to instance (not stored) |
| webhook | object | No | Webhook configuration for task completion notification |
| webhook.url | string | No | HTTPS URL to receive webhook |
| webhook.auth | string | No | Authorization header value |
| webhook.name | string | No | Webhook identifier |
| webhook.submittedData | enum | No | Payload typefull_response | structured_output | just_ping |
| policyId | string | No | Policy ID to apply automation guardrails (domain restrictions, capability controls, LLM role). Optional. |
| timezone | string | No | IANA timezone name for the session, e.g. "America/New_York", "Europe/London", "Asia/Tokyo". Date/time-sensitive instructions (e.g. "tomorrow morning", "today", "in 2 hours") are interpreted in this timezone. When omitted, follows the WebRun proxy country if one is set (e.g. country "de" → Europe/Berlin); otherwise the browser default. |
| outputType | enum | No | Response format (default: text)text | structured_json | structured_csv |
| maxDuration | number | No | Max duration in minutes (default: 20, max: 60) |
| startingUrl | string | No | Optional starting URL |
| outputSchema | object | No | JSON Schema for structured output (required if outputType is structured_json) |
| environmentId | string | No | Environment ID for persistent profile session. Use list_environments to find available IDs. Without this, a disposable instance is used. |
| reach_out_mode | enum | No | Controls proactive chat-platform messages (Telegram/WhatsApp/Slack/Discord/Teams) to bot users on the same environment. Default: "off" — no messages are sent unless this is set explicitly. "guardrail_only" forwards guardrail prompts (CAPTCHA/2FA/verification) to chat when the API caller is offline. "full" also forwards the task result on completion. Each bot user additionally filters by their own reachOutMode preference.off | guardrail_only | full |
Details
The maintainer has not added details yet. Check the README in the repository.
Comments
Markdown supported
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.