databricks-solutions

Query Agent — Development skill for Claude Code

Development community

Query Deployed Databricks Agent Endpoints.

How to install Query Agent

Installs to ~/.claude/skills/databricks-solutions-agents-with-mcp-on-databricks-apps-query-agent/SKILL.md

Terminal

mkdir -p ~/.claude/skills/databricks-solutions-agents-with-mcp-on-databricks-apps-query-agent && curl -fsSL https://raw.githubusercontent.com/databricks-solutions/agents-with-mcp-on-databricks-apps/HEAD/.claude/skills/query-agent.md -o ~/.claude/skills/databricks-solutions-agents-with-mcp-on-databricks-apps-query-agent/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Query Agent does

Query Deployed Databricks Agent Endpoints

Use `mlflow.deployments` to query deployed agent endpoints. This is the recommended client for all serving endpoint types.

import mlflow.deployments
client = mlflow.deployments.get_deploy_client("databricks")
response = client.predict(endpoint=endpoint_name, inputs={...})

Do NOT use:

DatabricksOpenAI for serving endpoints (security issues)
w.serving_endpoints.query() (doesn't parse agent responses correctly)

ChatAgent Endpo

Alternatives in Development

Notebooklm Skill — Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks 5.9k ★
Cq — An open standard for shared agent learning 1.3k ★
Crypto Market Rank — Query crypto market rankings including trending tokens, smart money inflows, meme rankings, and top trader PnL 483 ★