MCP.so
Sign In
D

Data Product Mcp

@entropy-data

Repository

About Data Product Mcp

No overview available yet

#data-product#data-mesh#data-governance

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "dataproduct": {
      "command": "uvx",
      "args": [
        "dataproduct_mcp"
      ],
      "env": {
        "DATAMESH_MANAGER_API_KEY": "dmm_live_user_...",
        "DATAMESH_MANAGER_HOST": "https://api.datamesh-manager.com",
        "SNOWFLAKE_USER": "",
        "SNOWFLAKE_PASSWORD": "",
        "SNOWFLAKE_ROLE": "",
        "SNOWFLAKE_WAREHOUSE": "COMPUTE_WH",
        "DATABRICKS_HOST": "adb-xxx.azuredatabricks.net",
        "DATABRICKS_HTTP_PATH": "/sql/1.0/warehouses/xxx",
        "DATABRICKS_CLIENT_ID": "",
        "DATABRICKS_CLIENT_SECRET": "",
        "BIGQUERY_CREDENTIALS_PATH": "/path/to/service-account-key.json"
      }
    }
  }
}

Tools

4

Structured list of data products with their ID, name and description, owner information, and source of the result.

Data product details with enhanced output ports, including access status and inlined data contracts

Access request details including access_id, status, and approval information

Query results as structured data (limited to 100 rows)

Overview

What is Data Product MCP?

A Model Context Protocol (MCP) server that enables AI agents to discover data products in Data Mesh Manager, request governed access, and execute SQL queries against data platforms such as Snowflake, Databricks, and BigQuery.

How to use Data Product MCP?

Install via uvx and add the server configuration to your MCP client’s settings, supplying environment variables for authentication to Data Mesh Manager and your chosen data platform. Four tools are exposed: dataproduct_search, dataproduct_get, dataproduct_request_access, and dataproduct_query.

Key features of Data Product MCP

  • Discover data products via search term in Data Mesh Manager
  • Retrieve detailed product metadata and data contracts
  • Request and manage access to specific output ports
  • Execute SQL queries on governed data products
  • Supports Snowflake, Databricks, and BigQuery
  • Enforces data governance and access controls

Use cases of Data Product MCP

  • AI agents answer business questions by querying approved data products
  • Automate data discovery and access requests within governed data meshes
  • Enable self-service analytics with embedded governance policies
  • Integrate language models with enterprise data platforms securely

FAQ from Data Product MCP

What data platforms are supported?

Snowflake, Databricks, and BigQuery are explicitly supported, each with specific environment variable configuration.

Do I need access to a data product to query it?

Yes—the dataproduct_query tool requires active access to the output port. Access can be requested via dataproduct_request_access.

How are access requests handled?

Access may be automatically granted or require manual approval from the data product owner, depending on the product configuration and data governance rules.

What authentication is required?

A Data Mesh Manager API key (DATAMESH_MANAGER_API_KEY) is required. For data platforms, you need credentials (e.g., Snowflake PAT, Databricks OAuth, BigQuery service account key).

Does the server support self-hosted Data Mesh Manager?

Yes—set the DATAMESH_MANAGER_HOST environment variable to your instance URL.

Frequently asked questions

What data platforms are supported?

Snowflake, Databricks, and BigQuery are explicitly supported, each with specific environment variable configuration.

Do I need access to a data product to query it?

Yes—the `dataproduct_query` tool requires active access to the output port. Access can be requested via `dataproduct_request_access`.

How are access requests handled?

Access may be automatically granted or require manual approval from the data product owner, depending on the product configuration and data governance rules.

What authentication is required?

A Data Mesh Manager API key (`DATAMESH_MANAGER_API_KEY`) is required. For data platforms, you need credentials (e.g., Snowflake PAT, Databricks OAuth, BigQuery service account key).

Does the server support self-hosted Data Mesh Manager?

Yes—set the `DATAMESH_MANAGER_HOST` environment variable to your instance URL.

Comments

Basic information

Category

Data & Analytics

Transports

stdio

Author

entropy-data

Submitted by

jochenchrist

More Data & Analytics MCP servers

Sugra API MCP

Sugra Systems, Inc.

Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl

1

Jitsu

Jitsu

Jitsu is an open-source Customer Data Platform — an MIT-licensed alternative to Segment. This MCP server gives your AI assistant direct control over a Jitsu workspace, so you can run and debug data pipelines in conversat

Batru

Batru

Real, calibrated win-rate predictions, pick recommendations, counters, synergy and tier lists for Dota 2, Deadlock and Marvel Rivals, from production models trained on ~20M matches. Free hosted endpoint (Streamable HTTP)

Bounce Watch - Company Signal Intelligence

bouncewatch

Bounce Watch tells you what just changed at a company, and when. Who raised money. Who hired a senior person. Who opened an office, won a customer, or announced a partnership. Every event carries its own date, so you ca

SiteGuru

Your site's real SEO data in your AI assistant. SiteGuru crawls your website and connects to Google Search Console and Google Analytics. This server exposes that data to your assistant, so you can ask what's broken, wha