skills.rest
bcheng004
bcheng004COMMUNITY
Explore all skills by this author →
WebsiteGitHub

add-tools

Align MCP tool registration with databricks.yml resource permissions.

2|Updated Apr 6, 2026
Search Tags:#permissions#agent framework#mcp#runtime errors#databricks#databricks.yml#tools configuration
One-click install
npx skills add https://github.com/bcheng004/agent-langgraph-advanced-workshop --skill add-tools-bcheng004
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: add-tools
Source: https://github.com/bcheng004/agent-langgraph-advanced-workshop/tree/main/.claude/skills/add-tools
Command: npx skills add https://github.com/bcheng004/agent-langgraph-advanced-workshop --skill add-tools-bcheng004

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill prevents runtime permission errors by guiding you to both register new agent tools (like MCP servers and related resources) and grant the required access in databricks.yml.

Core Features & Use Cases

  • MCP tool enablement: Add MCP servers (e.g., Genie spaces, vector search, UC functions) to the agent by updating agent_server/agent.py with DatabricksMCPServer and DatabricksMultiServerMCPClient.
  • Permission provisioning: Add the matching resources entries in databricks.yml so the deployed app is allowed to use the tool at runtime.
  • Operational troubleshooting: Covers common failure modes such as missing permissions, value_from mismatches, and MCP tool call error handling to return errors to the LLM instead of crashing.

Quick Start

Tell the AI to update your agent to connect to a new Genie space MCP server and then modify databricks.yml to grant the required CAN_RUN permissions, including any needed value_from wiring.

Frequently Asked Questions about add-tools

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fix Databricks agent runtime permission errors for MCP tools?▼

Fix Databricks agent runtime permission errors by aligning tool registration in agent.py with matching resource permissions in databricks.yml, ensuring consistent value_from references for MCP servers.

How do I add a Genie space MCP server to a Databricks agent?▼

Add a Genie space MCP server by updating agent.py with DatabricksMCPServer and then modifying databricks.yml to grant the required CAN_RUN permissions for the deployed app.

Why does my Databricks agent crash when calling an MCP tool?▼

Your agent may crash from missing permissions or value_from mismatches; implement handle_tool_error and timeout tuning in your MCP configuration to return errors to the LLM instead.

What databricks.yml entries are needed for Unity Catalog functions in an agent?▼

Configure databricks.yml entries for Unity Catalog functions by adding matching resources with consistent value_from wiring to grant the deployed app runtime access to the tool-backed resources.

How do I configure DatabricksMultiServerMCPClient for vector search tools?▼

Configure vector search tools by updating agent.py with DatabricksMultiServerMCPClient and adding the required resource permissions in databricks.yml to prevent execution time failures.

Related Skills

Explore More Software Engineering Skills→
victorlouvictorlou
4

add-tools

Add MCP servers and grant Databricks permissions in databricks.yml.

Community
Intermediate
kollaboraikollaborai
1

debug-mcp-integration

Diagnose MCP server connection failures, tool registration issues, and execution errors.

Community
Intermediate
AnanyaDBJAnanyaDBJ
6

discover-tools

Identify Databricks tools in a workspace for AI agent integration.

Community
Intermediate
leary-pokenleary-poken
1

databricks-asset-bundles

Automate multi-environment Databricks Asset Bundles configuration and deployment.

Community
Advanced