feat(prompts_sample): add sample for mcp prompts

Author: giuliastf

samples/mcp-refactoring-assistant/.agent/CLI_REFERENCE.md

@@ -0,0 +1,92 @@
+## Required Agent Structure
+
+**IMPORTANT**: All UiPath coded agents MUST follow this standard structure unless explicitly specified otherwise by the user.
+
+### Required Components
+
+Every agent implementation MUST include these three Pydantic models:
+
+```python
+from pydantic import BaseModel
+
+class Input(BaseModel):
+    """Define input fields that the agent accepts"""
+    # Add your input fields here
+    pass
+
+class State(BaseModel):
+    """Define the agent's internal state that flows between nodes"""
+    # Add your state fields here
+    pass
+
+class Output(BaseModel):
+    """Define output fields that the agent returns"""
+    # Add your output fields here
+    pass
+```
+
+### Required LLM Initialization
+
+Unless the user explicitly requests a different LLM provider, always use `UiPathChat`:
+
+```python
+from uipath_langchain.chat import UiPathChat
+
+llm = UiPathChat(model="gpt-4o-2024-08-06", temperature=0.7)
+```
+
+**Alternative LLMs** (only use if explicitly requested):
+- `ChatOpenAI` from `langchain_openai`
+- `ChatAnthropic` from `langchain_anthropic`
+- Other LangChain-compatible LLMs
+
+### Standard Agent Template
+
+Every agent should follow this basic structure:
+
+```python
+from langchain_core.messages import SystemMessage, HumanMessage
+from langgraph.graph import START, StateGraph, END
+from uipath_langchain.chat import UiPathChat
+from pydantic import BaseModel
+
+# 1. Define Input, State, and Output models
+class Input(BaseModel):
+    field: str
+
+class State(BaseModel):
+    field: str
+    result: str = ""
+
+class Output(BaseModel):
+    result: str
+
+# 2. Initialize UiPathChat LLM
+llm = UiPathChat(model="gpt-4o-2024-08-06", temperature=0.7)
+
+# 3. Define agent nodes (async functions)
+async def process_node(state: State) -> State:
+    response = await llm.ainvoke([HumanMessage(state.field)])
+    return State(field=state.field, result=response.content)
+
+async def output_node(state: State) -> Output:
+    return Output(result=state.result)
+
+# 4. Build the graph
+builder = StateGraph(State, input=Input, output=Output)
+builder.add_node("process", process_node)
+builder.add_node("output", output_node)
+builder.add_edge(START, "process")
+builder.add_edge("process", "output")
+builder.add_edge("output", END)
+
+# 5. Compile the graph
+graph = builder.compile()
+```
+
+**Key Rules**:
+1. Always use async/await for all node functions
+2. All nodes (except output) must accept and return `State`
+3. The final output node must return `Output`
+4. Use `StateGraph(State, input=Input, output=Output)` for initialization
+5. Always compile with `graph = builder.compile()`

samples/mcp-refactoring-assistant/.agent/REQUIRED_STRUCTURE.md

@@ -0,0 +1 @@
+ANTHROPIC_API_KEY=***

samples/mcp-refactoring-assistant/.agent/SDK_REFERENCE.md

@@ -0,0 +1,21 @@
+# Agent Code Patterns Reference
+
+This document provides practical code patterns for building UiPath coded agents using LangGraph and the UiPath Python SDK.
+
+---
+
+## Documentation Structure
+
+This documentation is split into multiple files for efficient context loading. Load only the files you need:
+
+1. **@.agent/REQUIRED_STRUCTURE.md** - Agent structure patterns and templates
+   - **When to load:** Creating a new agent or understanding required patterns
+   - **Contains:** Required Pydantic models (Input, State, Output), LLM initialization patterns, standard agent template
+
+2. **@.agent/SDK_REFERENCE.md** - Complete SDK API reference
+   - **When to load:** Calling UiPath SDK methods, working with services (actions, assets, jobs, etc.)
+   - **Contains:** All SDK services and methods with full signatures and type annotations
+
+3. **@.agent/CLI_REFERENCE.md** - CLI commands documentation
+   - **When to load:** Working with `uipath init`, `uipath run`, or `uipath eval` commands
+   - **Contains:** Command syntax, options, usage examples, and workflows

samples/mcp-refactoring-assistant/.env.example

@@ -0,0 +1 @@
+@AGENTS.md

samples/mcp-refactoring-assistant/AGENTS.md

@@ -0,0 +1,64 @@
+# Code Refactoring Assistant with MCP
+
+A LangGraph agent that demonstrates how to use **MCP (Model Context Protocol)** for code analysis and refactoring guidance.
+
+## What It Does
+
+This agent analyzes Python code, detects issues (complexity, code smells, deep nesting), and provides tailored refactoring guidance using MCP prompts.
+
+Shows how to use `client.get_prompt()` to fetch prompt templates dynamically from an MCP server.
+
+
+## MCP Components
+
+### Server (`server.py`)
+Exposes:
+- **Tools**: Code analysis functions
+  - `analyze_code_complexity` - Detects complexity metrics
+  - `detect_code_smells` - Finds common issues
+  - `get_refactoring_guide` - Returns which prompt to use
+
+- **Prompts**: Refactoring templates
+  - `extract_method_prompt` - For long functions
+  - `simplify_conditional_prompt` - For nested conditions
+  - `remove_duplication_prompt` - For duplicate code
+  - `improve_naming_prompt` - For poor variable names
+
+### Client (`graph.py`)
+- Agent uses tools to analyze code
+- Agent determines which refactoring approach to use
+- **`client.get_prompt()`** fetches the appropriate template from MCP server
+- LLM generates final refactoring guidance
+
+## How to Run
+
+1. **Install dependencies**:
+```bash
+uv sync
+```
+
+2. **Initialize** (if needed):
+```bash
+uipath init
+```
+
+3. **Run the agent**:
+```bash
+uipath run agent --input-file input.json
+```
+
+## Example Input
+
+```json
+{
+  "code": "def process_data(x, y, z):\n    if x:\n        if y:\n            if z:\n                return x + y + z"
+}
+```
+
+## Example Output
+
+The agent will:
+1. Detect the issue (deep nesting)
+2. Fetch the `simplify_conditional_prompt` via MCP
+3. Generate refactoring guidance using guard clauses
+

samples/mcp-refactoring-assistant/CLAUDE.md

@@ -0,0 +1,8 @@
+flowchart TB
+  __start__(__start__)
+  agent(agent)
+  prompt(prompt)
+  __end__(__end__)
+  __start__ --> agent
+  agent --> prompt
+  prompt --> __end__

samples/mcp-refactoring-assistant/README.md

@@ -0,0 +1,4 @@
+{
+    "version": "2.0",
+    "resources": []
+}

samples/mcp-refactoring-assistant/agent.mermaid

@@ -0,0 +1,83 @@
+{
+    "$schema": "https://cloud.uipath.com/draft/2024-12/entry-point",
+    "$id": "entry-points.json",
+    "entryPoints": [
+        {
+            "filePath": "agent",
+            "uniqueId": "426f3cb2-ac10-4969-840e-399932250e3a",
+            "type": "agent",
+            "input": {
+                "type": "object",
+                "properties": {
+                    "code": {
+                        "title": "Code",
+                        "type": "string"
+                    }
+                },
+                "required": [
+                    "code"
+                ]
+            },
+            "output": {
+                "type": "object",
+                "properties": {
+                    "result": {
+                        "default": null,
+                        "title": "Result",
+                        "type": "string"
+                    }
+                },
+                "required": []
+            },
+            "graph": {
+                "nodes": [
+                    {
+                        "id": "__start__",
+                        "name": "__start__",
+                        "type": "__start__",
+                        "subgraph": null,
+                        "metadata": {}
+                    },
+                    {
+                        "id": "agent",
+                        "name": "agent",
+                        "type": "node",
+                        "subgraph": null,
+                        "metadata": {}
+                    },
+                    {
+                        "id": "prompt",
+                        "name": "prompt",
+                        "type": "node",
+                        "subgraph": null,
+                        "metadata": {}
+                    },
+                    {
+                        "id": "__end__",
+                        "name": "__end__",
+                        "type": "__end__",
+                        "subgraph": null,
+                        "metadata": {}
+                    }
+                ],
+                "edges": [
+                    {
+                        "source": "__start__",
+                        "target": "agent",
+                        "label": null
+                    },
+                    {
+                        "source": "agent",
+                        "target": "prompt",
+                        "label": null
+                    },
+                    {
+                        "source": "prompt",
+                        "target": "__end__",
+                        "label": null
+                    }
+                ]
+            }
+        }
+    ]
+}