// MCP TOOL REFERENCE

DATAHUB TOOLS

21 tools from the DataHub MCP Server, categorised by risk level.

// ALL 21 DATAHUB TOOLS

READ 9 tools

Read get_dataset_queries Fetch SQL queries referencing a dataset or column Read get_entities Fetch detailed metadata for entities by URN Read get_lineage Retrieve upstream or downstream lineage for an entity Read get_lineage_paths_between Retrieve lineage paths between two assets Read get_me Retrieve info about the authenticated user Read grep_documents Search within document content using regex Read list_schema_fields List schema fields for a dataset with filtering Read search Search DataHub using keyword search with boolean logic Read search_documents Search for documents using keyword search

WRITE 7 tools

Write add_owners Add ownership assignments to entities Write add_structured_properties Manage structured properties on entities Write add_tags Add tags to entities or schema fields Write add_terms Add glossary terms to entities or fields Write save_document Save documents to DataHub's knowledge base Write set_domains Assign domain membership for entities Write update_description Update or remove descriptions for entities

DESTRUCTIVE 5 tools

Destructive remove_domains Remove domain membership for entities Destructive remove_owners Remove ownership assignments from entities Destructive remove_structured_properties Remove structured properties from entities Destructive remove_tags Remove tags from entities or schema fields Destructive remove_terms Remove glossary terms from entities or fields

// RUNNING THIS SERVER

The managed route: connect DataHub through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @mcp-server-datahub

// FAQ

How many tools does the DataHub MCP server have? +

The DataHub MCP server exposes 21 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on DataHub tools? +

Route the DataHub server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do DataHub tools fall into? +

DataHub tools are categorised as Read (9), Write (7), Destructive (5). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.