get_entities
Fetch detailed metadata for one or more entities by URN
Part of the DataHub MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
WHEN AI AGENTS USE THIS TOOL
AI agents call get_entities to retrieve information from DataHub without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions — but you may still want rate limits to control API costs.
WHY ENFORCE A POLICY ON GET_ENTITIES
Even though get_entities only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
RECOMMENDED POLICY
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_entities:
rules:
- action: allowSee the full DataHub policy for all 21 tools.
DETAILS
MORE DATAHUB TOOLS
search Read get_lineage Read get_dataset_queries Read list_schema_fields Read get_lineage_paths_between Read get_me Read search_documents Read grep_documents Read SIMILAR READ TOOLS ON OTHER SERVERS
list_bases Airtable list_tables Airtable list_records Airtable get_record Airtable search_records Airtable search Amplitude RELATED READING
FREQUENTLY ASKED QUESTIONS
What does the get_entities tool do?
Fetch detailed metadata for one or more entities by URN. It is categorised as a Read tool in the DataHub MCP Server, which means it retrieves data without modifying state.
How do I enforce a policy on get_entities?
Add a rule in your Intercept YAML policy under the tools section for get_entities. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the DataHub MCP server.
What risk level is get_entities?
get_entities is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Can I rate-limit get_entities?
Yes. Add a rate_limit block to the get_entities rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
How do I block get_entities completely?
Set action: deny in the Intercept policy for get_entities. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
What MCP server provides get_entities?
get_entities is provided by the DataHub MCP server (mcp-server-datahub). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
ENFORCE POLICIES ON DATAHUB
Open source. One binary. Zero dependencies.