$ loading_
Search enterprise data, trace lineage, and generate usable SQL queries.
The available materials are sparse, but the MCP tool is open-source with no required secrets and no declared remote endpoints, and no clear high-risk red flags are evident. It does execute code and is designed for organizational data discovery and SQL generation, so it should be deployed with caution due to local execution and unclear data access scope.
The materials explicitly state that no keys or environment variables are required, and there is no indication that API tokens, database passwords, or other sensitive credentials are needed; based on the available facts, credential exposure appears limited.
No remote endpoints are declared, and the README provides no external service addresses; based on the current materials, there is no clear sign of data egress targets or user data being sent to unknown services.
The system checks explicitly indicate that it executes code; this is a normal MCP-tool capability and should be treated as standard local process/code execution risk. The materials do not show any unusual system permission requests, but the runtime environment should still be constrained.
The description says it can search an organization's data ecosystem, inspect lineage, and generate SQL, indicating possible access to data catalogs, metadata, or related business context; however, the materials do not specify exact read/write scope, whether it performs writes, or whether permissions are excessive, so actual data boundaries should be reviewed carefully.
Positive factors include public source code and an Apache 2.0 license, making code review possible; however, the source is a third-party registry, the repository has 0 stars, and maintenance status is unknown, so supply-chain maturity and ongoing maintenance signals are weak. Review the code and dependencies before use.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "DataHub MCP Server" yet — see the docs or source repo.
Help me find the tables, fields, and metric definitions related to user retention analysis, and explain how they relate to each other.
A list of relevant tables and fields, business definitions, and a brief summary of how the tables relate.
Trace the data lineage for the 'monthly active users' metric, including upstream tables and transformations.
An overview of upstream sources, transformation steps, and key dependencies behind the metric.
Based on the existing data model, generate SQL to count new user registrations by channel over the last 90 days, and note the source tables and fields used.
Executable SQL plus notes on the referenced tables, fields, and their purposes.
Connect to DataHub catalogs to find datasets, trace lineage, and read metadata.
Connect AI to HubSpot for CRM actions, marketing tasks, and data access.
Unifies MCP clients with tool routing, memory, and automation flows.
Explore Databricks metadata, run SQL, and analyze lineage for data discovery.
Manage hubNote workspaces, pages, and data rows using natural language.
Manage and search HubSpot CRM contacts, companies, and deals with natural language.