Connect AI agents to the Plaid Dashboard MCP server

Setup

1. Install the SDK

   • Node.js
   • Python

   npm install @scalekit-sdk/node dotenv

2. Set your credentials

   Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>

3. Create the Plaid Dashboard MCP connection

   In AgentKit > Connections, create a Plaid Dashboard MCP connection. The name you give it is the connection_name your code passes. See Configure connections.

   Console steps with screenshots

   Plaid Dashboard MCP connections sign in to Plaid’s hosted Dashboard MCP server with your Plaid client ID and Production secret. The server gives your agent your team’s Plaid Dashboard diagnostics and analytics: Item debugging, Link conversion analytics and API usage. It doesn’t return end users’ bank data; for that, use the Plaid connector.

   Your Plaid team must be approved for Production access with at least one Plaid product. The server works with Production data only.

   1. Copy your Plaid keys

      In the Plaid Dashboard, open Developers > Keys and copy your client ID and your Production secret. Sandbox secrets are not accepted.

   2. Create the connection

      In the Scalekit dashboard, go to AgentKit > Connections > Create Connection, find Plaid Dashboard MCP and click Create. The connection name is the connection_name your code passes.

   3. Add a connected account

      To test, open the connection, click the Connected Accounts tab > Add Account, enter the user’s identifier, such as user_123, and fill in Client ID and Production Secret.

      In production, each user opens the authorization link and enters the same fields there.

      Scalekit exchanges the client ID and secret for a short-lived access token with the mcp:dashboard scope, and gets a new one when it expires. You don’t request tokens yourself.

4. Authorize a user and call the API

   Once a user authorizes the connection, call the Plaid Dashboard MCP server API through the Scalekit proxy with actions.request: Scalekit adds the user's credentials to each request. See Call any API.