Runwork
For AI Agents

One workspace.
Every AI tool.

Your AI agent connects to Runwork and gets access to your team's data, integrations, workflows, and skills. Via MCP, CLI, or knowledge files. Any agent, one workspace.

Get started MCP docs

Supported agents

runwork setup auto-detects and configures these agents.

Claude Code Claude Code MCP + Skills
Claude Desktop Claude Desktop MCP + Skills
Cursor Cursor MCP + Skills
Codex Codex MCP + Skills
Windsurf Windsurf MCP + Skills
Copilot (VSCode) Copilot (VSCode) MCP
Copilot CLI Copilot CLI MCP
Gemini CLI Gemini CLI MCP + Skills

Any MCP-compatible tool can also connect manually using your workspace endpoint URL and API key.

How agents connect

MCP (Model Context Protocol)

Every workspace exposes an MCP server. Your AI agent connects once and gets tools for everything: entities, workflows, schedules, integrations, files, channels, skills.

Streamable HTTP and SSE transports. Standard protocol. Works with any MCP-compatible tool.

Learn more

Runwork CLI

Full terminal interface to the workspace. Every command supports --json for machine-readable output that AI agents parse natively.

runwork agents, runwork entities, runwork workflows, runwork integrations, runwork files, and more.

Learn more

Skills (SKILL.md)

Every app auto-generates a skill file with capability descriptions, API references, and domain knowledge. Your agent reads it and understands what's available.

YAML frontmatter + markdown. Portable to any AI tool. Downloaded from dashboard or synced via CLI.

Learn more

Knowledge files (CLAUDE.md, AGENTS.md)

When any AI agent creates or opens a Runwork app (via runwork init or runwork dev), the platform generates knowledge files on the fly. This works for any agent: Claude Cowork on the desktop creating a workflow, Claude Code building a full app, or Cursor adding an endpoint. The agent understands Runwork from the first prompt.

Created automatically. Always up to date. Works with Claude Cowork, Claude Code, Cursor, Codex, and any agent that reads project files.

Learn more

What your agent can do

Once connected, your AI agent gets tools for everything in your workspace.

✓
Query entities

Read and write workspace data: customers, orders, products, any entity type.

✓
Trigger workflows

Start multi-step automations with parameters.

✓
Run schedules

Trigger scheduled jobs on demand or check their history.

✓
Call integrations

Make API calls to 3,200+ connected services: HubSpot, Stripe, Slack, Google, and more.

✓
Upload and download files

Manage workspace file storage. Upload reports, download data files.

✓
Send channel messages

Post messages to team channels, notify teammates, share results.

✓
List and load skills

Browse available skills and load them for context-aware conversations.

✓
Manage agents

List agents, check status, view execution history, trigger task agents.

✓
Call endpoints

Hit public API endpoints exposed by workspace apps.

✓
Delegate to sandboxes

Run complex tasks in isolated compute environments with full code execution.

Connect in 60 seconds

Terminal
# Install the CLI
$ curl -fsSL https://runwork.ai/install.sh | sh
# Authenticate
$ runwork login
# Configure all local AI agents
$ runwork setup
Detected agents:
✓ Claude Code
✓ Claude Desktop
✓ Cursor
✓ 12 skills synced
✓ 4 MCP servers configured
✓ Your agents are connected to the workspace

That's it. Your AI agents now have access to your workspace's data, integrations, workflows, and skills.

Connect your agents today.

One workspace. Every AI tool your team uses.

Get started