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

modify-agent

Modify Databricks LangChain agent code to add MCP tools and update configuration.

2|Updated Apr 6, 2026
Search Tags:#fastapi#langgraph#responses api#databricks#mcp tools#system instructions#agent modification
One-click install
npx skills add https://github.com/bcheng004/agent-langgraph-advanced-workshop --skill modify-agent-bcheng004
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: modify-agent
Source: https://github.com/bcheng004/agent-langgraph-advanced-workshop/tree/main/.claude/skills/modify-agent
Command: npx skills add https://github.com/bcheng004/agent-langgraph-advanced-workshop --skill modify-agent-bcheng004

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you rapidly change an existing agent’s capabilities and runtime behavior without getting stuck on boilerplate code or integration details.

Core Features & Use Cases

  • Update agent configuration and instructions: Adjust model selection, system instructions, and agent message-wrapping patterns so changes actually take effect.
  • Add or rewire tools via MCP: Integrate Databricks MCP servers (UC functions, Vector Search indexes, Genie spaces, or external MCP endpoints) so the agent can call new capabilities.
  • Align SDK usage with Responses API patterns: Convert streaming events and correctly structure messages for ResponsesAgent-style agents.

Quick Start

Ask the AI to modify agent_server/agent.py to add a new MCP tool and update the agent instructions to match the correct system-message pattern for LangGraph Responses API streaming.

Frequently Asked Questions about modify-agent

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

FAQPage Schema
How do I add MCP tools to an existing Databricks LangChain agent?▼

To add MCP tools to a Databricks LangChain agent, you modify agent_server/agent.py to integrate UC functions, Vector Search, Genie, or external MCP endpoints and update the agent's server wiring.

Why aren't my updated system instructions taking effect in my Responses API agent?▼

Updated system instructions fail when message-wrapping patterns are incorrect. You must use the proper message-prepending approach for LangGraph Responses API streaming to ensure behavior changes actually take effect.

Can I use FastAPI to adjust model configuration and runtime behavior for LangGraph agents?▼

Yes, you can adjust model selection, update system instructions, and align SDK usage with Responses API patterns by updating the FastAPI and MLflow server wiring within the agent codebase.

What's the best way to convert streaming events for a ResponsesAgent-style agent?▼

The best way to convert streaming events is to apply the correct streaming event conversion utilities and structure messages properly within the LangGraph Responses API configuration.

How do I integrate Databricks Genie spaces or Vector Search into my agent codebase?▼

You integrate Genie spaces or Vector Search by configuring Databricks MCP servers within agent.py, allowing the agent to successfully call these new capabilities during runtime.

Related Skills

Explore More Software Engineering Skills→
databricksdatabricks
183

modify-agent

Modify agent code, integrate MCP servers, and update model configurations.

Official
Intermediate
jaimedhenriquesjaimedhenriques

copilot-sdk

Build Copilot SDK agent applications with session management and streaming responses.

Community
Advanced
AshDaxAshDax

discover-tools

Discover Databricks workspace tools and resources across catalogs and schemas.

Community
Intermediate
keqingli1129keqingli1129

modify-agent

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

Community
Intermediate