Getting Started
Overview of the PlaidCloud MCP server — what it exposes, authentication options, and the basics every AI agent client needs.
PlaidCloud exposes a curated Model Context Protocol (MCP) server at /mcp/ on every workspace. AI agents connect to it the same way they connect to any other MCP server, then call the tools to read projects, run workflows, query tables, manage dimensions, and more.
The pages in this section cover what the server exposes, how to authenticate, and step-by-step setup for the most common AI clients.
Claude Code
Set up Claude Code (CLI, VSCode extension, JetBrains plugin) to call PlaidCloud's MCP tools using either OAuth or a static Bearer token.
Claude Desktop and Claude.ai
Add PlaidCloud as a Custom Connector in Claude.ai (web) or Claude Desktop so the chat assistant can call MCP tools during conversations.
Cursor
Configure Cursor IDE to call PlaidCloud's MCP tools through its built-in MCP support.
GitHub Copilot
Configure GitHub Copilot's agent mode in VSCode to use PlaidCloud's MCP tools.
Google Gemini CLI
Configure Google's gemini-cli to call PlaidCloud's MCP tools.
ChatGPT
Current state of MCP support in ChatGPT and recommended approaches for connecting ChatGPT to PlaidCloud.
Troubleshooting
Common issues connecting AI agents to the PlaidCloud MCP server and how to fix them.