Ask your AI agent what Smart Money is doing

Add the Datadash MCP server to Claude Code, Cursor, Codex or VS Code. Ask in plain English; your assistant writes the queries.

Connect it in three steps

Datadash hosts the server, so there is nothing to run.

  1. Create an API key

    Open Settings, then API Keys, and create one. It is shown once. Make a separate key for your assistant, so you can revoke that one on its own.

    Open API Keys
  2. Add Datadash to your client

    Pick your client. Where it can, Datadash installs as a plugin, which adds skills such as wallet analysis and smart money.

    Claude Code

    Inside Claude Code
    /plugin install datadash --marketplace datadash-xyz/mcp-skills-plugin

    Needs Claude Code 2.1.275 or later. Confirm the marketplace, choose a scope, then enter your Datadash API key when prompted.

    Claude app

    Add marketplace
    datadash-xyz/mcp-skills-plugin

    Open Customize, then Plugins. Select Add marketplace, enter this repository and install Datadash. Then connect it from its Connectors tab.

    Codex

    Terminal
    export DATADASH_API_KEY=<your-api-key>
    codex plugin marketplace add datadash-xyz/mcp-skills-plugin

    Then run /plugins inside Codex, select Datadash and install it.

    Cursor

    ~/.cursor/mcp.json
    {
      "mcpServers": {
        "datadash": {
          "url": "https://api.datadash.xyz/mcp",
          "headers": {
            "X-Api-Key": "<your-api-key-here>"
          }
        }
      }
    }

    Use .cursor/mcp.json instead to limit it to one project. A green dot next to datadash in Cursor Settings means it is connected.

    VS Code

    .vscode/mcp.json
    {
      "inputs": [
        {"type": "promptString", "id": "datadash-api-key", "description": "Datadash API key", "password": true}
      ],
      "servers": {
        "datadash": {
          "type": "http",
          "url": "https://api.datadash.xyz/mcp",
          "headers": {"X-Api-Key": "${input:datadash-api-key}"}
        }
      }
    }

    The inputs entry has VS Code ask for the key once and store it, so it never sits in the file. Select Start above the datadash entry, then use Chat in agent mode.

    Gemini CLI

    Terminal
    gemini extensions install https://github.com/datadash-xyz/mcp-skills-plugin

    Enter your Datadash API key when prompted. It is stored as DATADASH_API_KEY.

    Other clients

    Most clients
    {
      "mcpServers": {
        "datadash": {
          "type": "http",
          "url": "https://api.datadash.xyz/mcp",
          "headers": {"X-Api-Key": "<your-api-key-here>"}
        }
      }
    }

    Any client that speaks Streamable HTTP and can send a custom header will work. The server is stateless: every request is authenticated on its own, and no session carries over between them.

  3. Ask your first question

    Start a new chat and ask about the data. Your assistant works out the table, the fields and the filters itself.

    • Who are the top 10 wallets by realized PnL in crypto markets?
    • What is smart money positioned on in the biggest active politics markets?
    • Which markets resolving in the next 30 days have the biggest smart money edge among the top 1,000 traders?
    • Build a cohort of wallets with over $100k in volume and a win rate above 60%, then tell me what they are holding.

Your questions, answered

What the MCP server reaches, and what it does not.

Do I need a Datadash account?

Yes. The server authenticates with a Datadash API key, which you create under Settings, API Keys. Your account’s limits apply to tool calls too.

What can the assistant do with my key?

Everything your account can do, including creating, changing and deleting your cohorts. Create a key just for your MCP client, so you can revoke it without affecting anything else.

Which AI tools can connect to it?

The setup above has steps for Claude Code, the Claude app, Codex, Cursor, VS Code and Gemini CLI. Any other client that speaks Streamable HTTP and can send a custom header works too.

Is there a plugin?

Yes. The Datadash AI plugin installs this server together with skills, such as wallet analysis and smart money, that teach your assistant which tables answer which question and how to read the numbers. It works with Claude on the web and desktop, Claude Code, Codex and Gemini CLI, and still needs your Datadash API key. Get the plugin on GitHub

Is it the same data as the app?

Yes. A tool call runs through the same filters, validation and authentication as the equivalent REST request, so anything you ask here you can reproduce with curl.

Where does the data come from?

Datadash indexes Polymarket trades directly from the Polygon blockchain, and calculates PnL, ranks, Signals and Smart Money from them. Market names and images come from Polymarket.

Is it affiliated with Polymarket?

No. Datadash is an independent company. The MCP server is not affiliated with or endorsed by Polymarket.