> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/consume/consume-with-ai/connect-clients/claude.md). # Claude Connecting Claude to Data Product MCP lets it answer your questions from governed Data Products instead of guessing — discovery, querying, quality checks, lineage, and owner lookup all run against trusted, authorized data. From the Data Product page, select **Activate → MCP**, then select **View install guide** on the **Claude Desktop** or **Claude Code** card to open the step-by-step guide. ## Prerequisites You need: * Your DataOS instance URL, such as `pacific-051426.dataos.cloud`. * A DataOS API token generated from [Home → Generate API tokens](/consume/get-started/readme-1.md#get-a-dataos-api-token). {% hint style="warning" %} **API token security.** API tokens are secrets. Don't commit them to source control. If you store the token in a config file, exclude that file from version control via `.gitignore`, or inject it through an environment variable at runtime. {% endhint %} ## Claude Code Run the following command in your terminal. Replace `` and `` with your values. ```bash claude mcp add --transport http DataProduct-MCP https:///dataproduct-mcp/api/v1 --header "apikey: " ``` Restart Claude Code and confirm **DataProduct-MCP** appears in the MCP tools list. ![Claude Code install guide showing the terminal command](/files/PA5b0aywpCAA7bA4wCJ8) ## Claude Desktop Claude Desktop requires the `mcp-remote` bridge package for remote HTTP MCP servers. ### Additional prerequisites * Node.js installed on your device. Download it from [nodejs.org](https://nodejs.org). ### Steps 1. Install `mcp-remote` globally. ```bash npm install -g mcp-remote ``` 2. Open the Claude Desktop config file. Go to **Settings → Developer** and click **Edit Config**, or open the file directly: * macOS: `~/Library/Application Support/Claude/claude_desktop_config.json` * Windows: `%APPDATA%\Claude\claude_desktop_config.json` 3. Paste the configuration below and save. Replace `` and `` with your values. ```json { "mcpServers": { "DataProduct-MCP": { "command": "npx", "args": [ "mcp-remote@latest", "https:///dataproduct-mcp/api/v1", "--header", "apikey: " ] } } } ``` 4. Quit and reopen Claude Desktop to apply the configuration. 5. In **Settings → Developer**, verify that **DataProduct-MCP** appears under configured MCP servers. ![Claude Desktop install guide showing the mcp-remote install and JSON configuration](/files/edgHWjDQtAbjOlMoWIQT) ## Verify the connection Ask Claude: ``` What data products are available to consume? ``` Claude should return Data Products from your DataOS instance, scoped to your token permissions. The data products and metrics shown below are an illustrative example from a sample catalog. What you see will depend on your own catalog and token permissions. ![Claude Desktop response listing available Data Products](/files/DYFDk6hyIVe9Cf1BZtBX)
Full response (example) Here are some of the data products available for consumption, scoped to your token permissions: | Data Product | Domain | Key Metrics | Updated | | ---------------------------------------------------------------------------------------------------------------------------------------- | ------------------- | ------------------------------------------------ | ---------- | | [Customer Account Health](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/customer-account-health) | customer-360 | account\_tier\_mix\_pct, active\_customer\_count | 2026-06-01 | | [Customer Delivery Reliability](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/customer-delivery-reliability) | customer-operations | on\_time\_pct, late\_orders, forecast\_change | 2026-06-01 | | [Receivables Health](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/receivables-health) | finance | AR aging buckets, dispute rate, distress flags | 2026-06-01 | | [Carrier Performance](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/carrier-performance) | logistics | on\_time\_pct, damage\_rate, dispute\_rate | 2026-06-01 | | [Production Performance](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/production-performance) | manufacturing | yield, scrap, rework, downtime | 2026-06-01 | | [Supplier Performance](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/supplier-performance) | procurement | rejection\_rate, fill\_rate, lead\_time | 2026-06-01 | | [Product Quality](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/product-quality) | quality | fail\_rate, defects\_per\_lot, SPC limits | 2026-06-01 | | [Orders360](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/orders360) | sales | revenue\_trend, order\_volume, customer\_growth | 2026-06-01 | | [Orders Analytics](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox/orders-analytics) | sales\_operations | daily\_order\_volume, daily\_revenue | 2026-05-26 | To see the full list and filter by domain, lifecycle, or tags, browse the catalog directly: [product-sandbox](https://pacific-051426.dataos.cloud/platform/data-product/product-sandbox)
--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://v2.dataos.info/consume/consume-with-ai/connect-clients/claude.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.