skills.rest
victorlou
victorlouCOMMUNITY
Explore all skills by this author →
GitHub

modify-agent

Modify LangGraph agent code, MCP servers, and Databricks permissions.

4|Updated May 9, 2026
Search Tags:#tool integration#configuration#LangGraph#MCP tools#Databricks#agent modification
One-click install
npx skills add https://github.com/victorlou/housing-assistant --skill modify-agent-victorlou
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: modify-agent
Source: https://github.com/victorlou/housing-assistant/tree/main/app/app-templates/.claude/skills/modify-langgraph-agent
Command: npx skills add https://github.com/victorlou/housing-assistant --skill modify-agent-victorlou

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you change an existing LangGraph-based agent when you need new tools, updated instructions, or different model/configuration settings without rebuilding everything from scratch.

Core Features & Use Cases

  • Agent code modification: Locate and edit the main agent logic, model selection, and instruction wiring in the server code.
  • Tooling expansion with MCP: Add or reconfigure MCP servers (manual, UC functions, vector search indexes, or Genie Space) so the agent can call the right external capabilities.
  • Deployment-ready configuration updates: Adjust Databricks bundle configuration (for permissions and serving access) to ensure the modified agent can run successfully.

Quick Start

Modify the agent’s tools and instructions by editing agent_server/agent.py, then rewire MCP servers and update databricks.yml to grant any required access.

Frequently Asked Questions about modify-agent

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

FAQPage Schema
How do I add new MCP tools to an existing LangGraph agent?▼

To add new MCP tools to a LangGraph agent, you edit the agent_server/agent.py file to rewire MCP server integrations, then update databricks.yml to grant the necessary runtime access permissions.

Can I change the model selection and system instructions of my agent without rebuilding it?▼

You can change model selection and system instructions by modifying the main agent logic in agent_server/agent.py, allowing you to update configuration settings without rebuilding the agent from scratch.

What is the best way to update Databricks bundle configuration for a modified agent?▼

Updating Databricks bundle configuration involves adjusting databricks.yml to ensure serving access and proper permissions so that newly added Databricks tools are accessible at runtime.

Do I need to update permissions when enabling external capabilities for my agent?▼

You need to update permissions in databricks.yml when enabling new external capabilities, ensuring the modified LangGraph agent can successfully access and run the added tools at runtime.

Why are my newly added Databricks tools not accessible at runtime?▼

Newly added Databricks tools may not be accessible at runtime if the databricks.yml permissions were not updated to grant serving access after modifying the agent_server/agent.py file.

What types of MCP servers can I configure when modifying agent tool routing?▼

When modifying agent tool routing, you can configure manual MCP servers, Unity Catalog functions, vector search indexes, or Genie Space to ensure the agent calls the right external capabilities.

Related Skills

Explore More Software Engineering Skills→
keqingli1129keqingli1129

modify-agent

Modify LangGraph/LangChain agents by updating models, instructions, and MCP tools.

Community
Intermediate
thbehthbeh

databricks-model-serving

Deploy MLflow models and LangGraph AI agents to Databricks Model Serving endpoints.

Community
Advanced
victorlouvictorlou
4

create-tools

Create Databricks Genie spaces, Vector Search indexes, UC functions, and HTTP connections.

Community
Intermediate
RamVegirajuRamVegiraju
4

add-tools

Automate adding tools and granting permissions for a Databricks agent.

Community
Advanced