Skip to content

Add data-observability toolset to MCP Server docs#37651

Draft
heron-- wants to merge 2 commits into
masterfrom
devin.marsh/add-data-observability-mcp-toolset
Draft

Add data-observability toolset to MCP Server docs#37651
heron-- wants to merge 2 commits into
masterfrom
devin.marsh/add-data-observability-mcp-toolset

Conversation

@heron--

@heron-- heron-- commented Jun 22, 2026

Copy link
Copy Markdown
Contributor

What does this PR do? What is the motivation?

Adds the data-observability toolset to the MCP Server documentation.

Updates:

  • setup.md: Adds data-observability to the Available toolsets list
  • tools.md: Adds a full Data Observability section documenting all 16 tools in the toolset

Merge instructions

Merge readiness:

  • Ready for merge

Additional notes

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@github-actions

Copy link
Copy Markdown
Contributor

@github-actions

Copy link
Copy Markdown
Contributor

⚠️ Possible site support note detected

The following files have a site-region shortcode at the top of the page that mentions a feature being "not available" or "not supported":

  • content/en/mcp_server/setup.md

Are you trying to document site support for a product? If so, the site-region shortcode is not the recommended approach. See the Documenting site support guide for the preferred method.

### `get_data_catalog_schema`
*Toolset: **data-observability***\
*Permissions Required: `Monitors Read` or `APM Read`*\
Returns the entity type schema for every platform the organization has data in. Discovers active platforms (Snowflake, BigQuery, Databricks, dbt, and so on), their entity types, the containment hierarchy, and the filterable attribute names. Call this at the start of a data catalog conversation to learn which platforms, entity types, and filters are available.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

also returns default metrics available for each entity type, like dataset.freshness!

### `rank_data_entities_by_lineage_degree`
*Toolset: **data-observability***\
*Permissions Required: `Monitors Read` or `APM Read`*\
Ranks entities by their transitive lineage connectivity using a pre-built snapshot. Returns parent-level entities ranked by how many other entities they connect to (downstream or upstream). Useful for identifying the most critical or widely consumed tables.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't think parent-level entities is meaningful to the customer - we could probably just say tables, dashboards, and jobs. Even though it's not a complete list, I feel like it covers the important bits and is generic enough to imply that it's a summary, not a list of every node type.

Gets the custom user-defined descriptions for data entities by their IDs. Returns a map of entity ID to description with created and updated timestamps.

- Show me the custom descriptions for these three tables.
- What description has been set for entity `a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4`?

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

is this a real entityId? could just use <entityId> or something

Remove em-dashes to match page style, reword for declarative voice,
and restore unrelated CRLF lines.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants