Skip to main content

DataHub Agent Context

MCP tools for AI agents to search and query your DataHub metadata catalog — works with Claude, Cursor, Copilot, and any MCP-compatible AI assistant.

What you can do

  • Search datasets, dashboards, pipelines, and other data assets by name or description
  • Retrieve entity details — schema, lineage, ownership, tags, glossary terms, and more
  • Trace lineage upstream and downstream across your data assets
  • Mutate metadata — update descriptions, tags, owners, domains, and glossary terms
  • Build LangChain or Google ADK agents with pre-built tool bindings
  • Set up Snowflake AI agents with one CLI command

Installation

pip install datahub-agent-context

# With LangChain support
pip install "datahub-agent-context[langchain]"

Quickstart

LangChain agent

from datahub.sdk.main_client import DataHubClient
from datahub_agent_context.langchain_tools import build_langchain_tools

client = DataHubClient.from_env()

# Read-only tools (search, lineage, entity details)
tools = build_langchain_tools(client, include_mutations=False)

# Include write tools (tags, descriptions, owners, etc.)
tools = build_langchain_tools(client, include_mutations=True)

# DataHub Cloud: add Ask DataHub AI assistant
from datahub_agent_context.langchain_tools import build_langchain_cloud_tools
tools += build_langchain_cloud_tools(client, ask_datahub=True)

Snowflake AI agent setup

datahub agent create snowflake \
  --datahub-url https://your-datahub-instance \
  --datahub-token your-token

Available tools

Search — search(), search_documents(), grep_documents()

Entities — get_entities(), list_schema_fields()

Lineage — get_lineage(), get_lineage_paths_between()

Queries — get_dataset_queries()

Incidents — list_incidents()

Mutations — add_tags(), remove_tags(), update_description(), set_domains(), add_owners(), add_glossary_terms(), add_structured_properties(), save_document(), raise_incident(), resolve_incident()

Cloud-only — ask_datahub_chat() (DataHub Cloud AI assistant)

Metadata

Release files for datahub-agent-context 1.7.0.20

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for datahub-agent-context 1.7.0.20
File Size Uploaded Provenance Actions
datahub_agent_context-1.7.0.20.tar.gz 111.3 kB Without provenance Details for datahub_agent_context-1.7.0.20.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for datahub-agent-context 1.7.0.20
File Interpreter ABI Platform Actions
datahub_agent_context-1.7.0.20-py3-none-any.whl Python 3 none any Details for datahub_agent_context-1.7.0.20-py3-none-any.whl

Total release size: 263.0 kB

Release files / datahub_agent_context-1.7.0.20.tar.gz

Download URL datahub_agent_context-1.7.0.20.tar.gz
Size 111.3 kB
Tags Source
SHA-256 checksum
How to use checksums
348f7f9b5bda4dfeccf8479462093e51964494401e4a4dab91ebfb171232006c
BLAKE2b-256 checksum
How to use checksums
0237255b8c55cf5dcd56f1fa124ecf288831c003b6e150b2d50376ef763506c2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.22

Release files / datahub_agent_context-1.7.0.20-py3-none-any.whl

Download URL datahub_agent_context-1.7.0.20-py3-none-any.whl
Size 151.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
3f0d8c2cb4b41108347dd8c6d15616b3492b450c147dbfb7655a49e68db54764
BLAKE2b-256 checksum
How to use checksums
8c7e155460c5c851e1c60075eed579aad50c1f7bebcf2e6fa026bc3af68fa109
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.10.22

Security for datahub-agent-context 1.7.0.20

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.7.0.20 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page