mcp-server-datahub

What is mcp-server-datahub?

An MCP (Model Context Protocol) server implementation for DataHub, an open-source context platform that gives organizations a single pane of glass across their entire data supply chain, unifying data discovery, governance, and observability. It enables AI agents to search, explore lineage, understand business context, and generate SQL using natural language.

How to use mcp-server-datahub?

Configure via environment variables (e.g., TOOLS_IS_MUTATION_ENABLED, TOOLS_IS_USER_ENABLED) and invoke the provided tools: search, get_lineage, get_dataset_queries, get_entities, list_schema_fields, get_lineage_paths_between, plus mutation tools when enabled. See the DataHub MCP server docs for detailed usage instructions.

Key features of mcp-server-datahub

• Structured search with wildcard, field, and boolean syntax
• SQL intelligence: fetch popular queries and generate accurate SQL
• Table and column-level lineage with upstream/downstream exploration
• Mutation tools: add/remove tags, terms, owners, domains, descriptions, structured properties
• Document tools: search, grep, save knowledge articles and FAQs
• User tools: retrieve authenticated user information

Use cases of mcp-server-datahub

• Find trustworthy data using natural language search across tables, columns, dashboards, and metrics
• Explore data lineage to understand impact of changes before they affect downstream users
• Navigate business glossaries, domains, data products, and asset relationships
• Generate accurate SQL queries using context like documentation, lineage, and popular queries
• Manage metadata: assign tags, glossary terms, owners, domains, and descriptions

FAQ from mcp-server-datahub

What tools does mcp-server-datahub provide?

It provides search, get_lineage, get_dataset_queries, get_entities, list_schema_fields, get_lineage_paths_between, plus mutation tools (add/remove tags, terms, owners, domains, descriptions, structured properties) and optional user and document tools.

How do I enable mutation tools?

Set the environment variable TOOLS_IS_MUTATION_ENABLED=true. By default mutation tools are disabled.

What environment variables are available for configuration?

Key variables include TOOLS_IS_MUTATION_ENABLED, TOOLS_IS_USER_ENABLED, DATAHUB_MCP_DOCUMENT_TOOLS_DISABLED, SAVE_DOCUMENT_TOOL_ENABLED, SAVE_DOCUMENT_PARENT_TITLE, TOOL_RESPONSE_TOKEN_LIMIT, ENTITY_SCHEMA_TOKEN_BUDGET, and SEMANTIC_SEARCH_ENABLED, among others.

Can I search within document content?

Yes, the grep_documents tool allows searching within document content using regex patterns. Document tools are automatically hidden if no documents exist in the catalog.

What is the maximum token limit for tool responses?

The default TOOL_RESPONSE_TOKEN_LIMIT is 80,000 tokens, and the schema token budget per entity is 16,000 tokens (ENTITY_SCHEMA_TOKEN_BUDGET).