One

"Get my last 5 emails from Gmail"

"Send a Slack message to #general: 'Meeting in 10 minutes'"

"Get all products from my Shopify store"

"Create a React form component that sends emails using Gmail"

"Build a dashboard that displays Linear users and their assigned projects with filtering"

"Create a paginatable table that fetches and displays QuickBooks invoices with search and sort"

Prefer not to run anything locally? One hosts a remote MCP server athttps://mcp.withone.ai/mcp. Point any MCP client that supports remote (HTTP) servers at that URL and authenticate with One via OAuth. There's nonpm installand noONE_SECRETto manage. You approve access in One's consent screen, where you can scope exactly which connections, actions, and permission levels the agent gets. Those choices are surfaced back to the agent through each connection'saccessfield, so it knows what it can run without searching.

Add it to your client's MCP configuration. The endpoint speaks the Streamable HTTP transport:

{ "mcpServers": { "one": { "type": "http", "url": "https://mcp.withone.ai/mcp" } } }

Some clients omittypeand take the URL alone; UI-based clients (custom connectors) just need the URL itself. On first connect, your client opens a browser to authenticate and authorize with One. After that, the same four tools are available.

The Windsurf link opens One's page in the editor's MCP marketplace, which is served from the official MCP registry where One is published asai.withone/mcp. Windsurf handles the OAuth sign-in itself once you install from that page.

If you prefer to configure the server manually instead of usingone init, install the package directly:

Then set the required environment variable:

Scope connections to a specific identity (e.g., a user, team, or organization):

ONE_IDENTITY=user_123 ONE_IDENTITY_TYPE=user

When set, the MCP server will only return connections associated with the specified identity. This is useful for multi-tenant applications where you want to scope integrations to specific users or entities.

Fine-tune what the MCP server can see and do:

ONE_PERMISSIONS=read ONE_CONNECTION_KEYS=conn_key_1,conn_key_2 ONE_ACTION_IDS=action_id_1,action_id_2 ONE_KNOWLEDGE_AGENT=true

All defaults preserve current behavior. If no access control env vars are set, the server starts with full access and all tools available.

Whatever you configure here is surfaced back to the agent:list_one_integrationsstamps each connection with anaccessfield so the agent knows up front what it can run there, without spending a turn searching. It is one of:

If you usedone init, the configuration below is already done for you. These examples are for reference or manual setups.

- Claude Desktop:MacOS:~/Library/Application\ Support/Claude/claude_desktop_config.json· Windows:%APPDATA%/Claude/claude_desktop_config.json
- Cursor:Open the Cursor menu and select "MCP Settings"

Magica is your all-in-one AI platform, offering 2500+ cutting-edge tools under a single subscription.

Turn your Make scenarios into callable tools for AI assistants.

Dynamically search and call tools using UnifAI Network

Connect your AI Agents to 8,000 apps instantly.

Connect AI assistants to Automatisch for workflow automation.

Unified MCP gateway that loads 150+ AI tools into Claude Desktop via a single Docker command on Windows. Routes tool calls across specialized servers (Business Intelligence, API Hub, Content Automation, Intelligence) with centralized logging and governance. Built for teams without dedicated platform engineers.

Connect AI assistants directly to the HiveFlow automation platform.

A hub server that connects to and manages other MCP servers.