# Skyvern — how to use (mcp.ai)

Connect your Skyvern account and use 10 tools for AI agents straight from your AI agent. Connect with your own API key. Skyvern automates browser-based workflows with AI agents that can navigate websites, extract data, and complete tasks.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_skyvern?ms=1787293500000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `skyvern_cancel_runs`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/skyvern`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/skyvern/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/skyvern/cancel/runs` — Cancel one or more active task or workflow runs in one request and report which IDs succeeded or failed.
  - body: { run_ids: string[] }
- `POST https://api.mcp.ai/api/skyvern/create/folder` — Create a folder for organizing Skyvern agents.
  - body: { title: string, description?: string }
- `POST https://api.mcp.ai/api/skyvern/delete/folder` — Delete a Skyvern folder without deleting the agents it contains.
  - body: { folder_id: string }
- `POST https://api.mcp.ai/api/skyvern/get/folder` — Get one Skyvern folder by ID, including its current agent count.
  - body: { folder_id: string }
- `POST https://api.mcp.ai/api/skyvern/get/run` — Get current status, output, errors, files, and observation links for a task or workflow run.
  - body: { run_id: string }
- `POST https://api.mcp.ai/api/skyvern/list/agents` — Search and list the latest versions of Skyvern agents available to the connected organization.
  - body: { search?: string, statuses?: string[], folder_id?: string, page_size?: integer, next_cursor?: string, only_workflows?: boolean, only_saved_tasks?: boolean }
- `POST https://api.mcp.ai/api/skyvern/list/folders` — Search and list folders used to organize Skyvern agents.
  - body: { search?: string, page_size?: integer, next_cursor?: string }
- `POST https://api.mcp.ai/api/skyvern/list/runs` — Find task and workflow runs for the connected organization, with status, type, workflow, and text filters.
  - body: { search?: string, statuses?: string[], page_size?: integer, run_types?: string[], next_cursor?: string, workflow_permanent_ids?: string[] }
- `POST https://api.mcp.ai/api/skyvern/start/browser/task` — Start an autonomous browser task that can navigate and interact with websites, including clicking and submitting forms. It may cause external side effects and consume Skyvern credits; use GET_RUN to m
  - body: { url?: string, title?: string, engine?: string, prompt: string, max_steps?: integer, webhook_url?: string, proxy_location?: string, start_fresh_browser?: boolean, data_extraction_schema?: object|string[]|string }
- `POST https://api.mcp.ai/api/skyvern/update/folder` — Change the title or description of an existing Skyvern folder.
  - body: { title?: string, folder_id: string, description?: string }

## Example prompts
- "What can I do in Skyvern?"
- "Show me a summary of my Skyvern account"

## More
- Page: https://mcp.ai/skyvern
- Agent spec (llms.txt): https://mcp.ai/skyvern/llms.txt
- Postman collection: https://mcp.ai/skyvern/postman.json