Automate adding tools and granting permissions for a Databricks agent.
npx skills add https://github.com/RamVegiraju/databricks-samples --skill add-tools
Please help me install this Agent Skill. Skill: add-tools Source: https://github.com/RamVegiraju/databricks-samples/tree/main/.claude/skills/add-tools-langgraph Command: npx skills add https://github.com/RamVegiraju/databricks-samples --skill add-tools
Add tools to your agent and grant required permissions in databricks.yml. Use when: (1) Adding MCP servers, Genie spaces, vector search, or UC functions to agent, (2) Permission errors at runtime, (3) User says 'add tool', 'connect to', 'grant permission', (4) Configuring databricks.yml resources.
Add a new MCP server entry in agent_server/agent.py and grant the required permissions in databricks.yml, then deploy and run the bundle to apply changes.
High-intent search queries and answers about installing and using this skill.
To add MCP servers and grant permissions to a Databricks agent, you must update agent_server/agent.py with the server entry and configure required access in databricks.yml, then deploy using databricks bundle deploy and run with bundle run to apply changes.
Connecting a Genie space or vector search to a Databricks agent requires adding the respective resource configuration to databricks.yml and updating agent_server/agent.py, using provided templates for uc-functions, uc-connections, or serving-endpoints to ensure proper deployment.
Runtime permission errors in a Databricks agent typically occur when required access settings are missing in databricks.yml. You must grant the necessary permissions for resources like UC functions or vector search before deploying the bundle.
The best way to configure Unity Catalog functions in databricks.yml is by applying the provided resource templates for uc-function and uc-connection, ensuring the agent has the correct permissions defined before executing databricks bundle deploy.
Yes, you can use databricks bundle deploy to apply permission grants for serving endpoints. You must define the serving-endpoint resources in databricks.yml and run the bundle to ensure the agent receives the required runtime access.
You need to update agent.py whenever you add new tools such as MCP servers, Genie spaces, or vector search to a Databricks agent, ensuring the codebase reflects the new connections before you deploy the bundle.
victorlouModify LangGraph agent code, MCP servers, and Databricks permissions.
keqingli1129Register MCP tools in agent_server/agent.py and grant Databricks resource permissions.
databricksConfigure Databricks agent access to external resources in databricks.yml.
AnanyaDBJAutomate tool setup and permission granting for Databricks agents.
