Skip to main content
Glama
Datris MCP Server

Datris MCP Server

find_data

Find datasets by meaning: rank readable pipelines against a natural-language query over names, tags, fields, and hosts. Returns location, freshness, lineage, and query hints without executing.

Instructions

Find datasets by meaning: ranks the pipelines your key can read against a natural-language query over their names, descriptions, tags, catalogs, destination field names, and source hosts. Each hit returns where the data lives, how fresh it is, provenance handles (latest run id, config version, script sha), lineage, and a howToQuery hint naming the existing query/search tool with pre-filled arguments. Discovery only — nothing is executed for you: make the query call yourself, then pass its provenance handles to ai_answer as sources so the answer carries them.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "find_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
aiNoRerank the top candidates with the platform's primary AI model (default: false — ranking is deterministic).
limitNoMaximum results to return (default: 5, max: 25).
queryYesNatural-language description of the data you need.
include_unity_catalogNoAlso search the Unity Catalog tables visible to every Databricks Platform secret your key can read (default: false). Warehouse hits follow the Datris hits, marked `source: "unity-catalog"`; `howToQuery` points at query_databricks only when a Datris pipeline owns the table, otherwise it is a plain SQL hint to run in your warehouse. Secrets without a known SQL warehouse are listed under `unityCatalog.skipped`. A stopped warehouse auto-starts on first use, which can add 5-20 s; a warehouse that does not answer within the per-secret time limit (45 s by default) is skipped rather than blocking the call. Up to `limit` warehouse hits are added on top of the Datris hits.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations supplied, the description carries the load and does disclose scope ('pipelines your key can read') and a critical behavioral trait ('nothing is executed for you'). It also describes the return payload in place of an output schema. It stops short of mentioning latency or cost characteristics of the optional warehouse path (those appear only in the parameter schema), so it is strong but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core purpose, then return-shape, then the usage handoff — a logical order with no filler. Despite being dense, every clause carries information an agent needs (search scope, payload, provenance handles, next step).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema and no annotations, the description covers what is needed: what is matched, what comes back (including freshness, lineage, and provenance handles), and what to do with the result. The remaining ambiguity is limited to pagination and warehouse latency details, which the input schema already documents.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description earns above that by expanding the `query` parameter's meaning into the concrete field set it is scored against, which the schema's one-line 'Natural-language description of the data you need' does not convey. The `ai` and `limit` parameters are left entirely to the schema, which is acceptable given its richness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Opening clause gives an exact verb and resource ('Find datasets by meaning') and immediately names the mechanism — semantic ranking of pipelines the key can read. It also enumerates the searchable fields (names, descriptions, tags, catalogs, destination field names, source hosts), so an agent knows precisely what kind of intent this matches versus a raw list/browse tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The last sentence is explicit routing: 'Discovery only — nothing is executed for you: make the query call yourself, then pass its provenance handles to ai_answer as sources.' It states what the tool does not do, names the downstream sibling to use next, and explains the handoff artifact, so there is no ambiguity about when this tool is the right entry point versus ai_answer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools