agent: mcp tools sample

.github/copilot-instructions.md

@@ -0,0 +1,40 @@
+# Copilot Instructions for Review
+
+Purpose:
+- Always use `**get_httpx_client_kwargs()` when creating `httpx.Client` or `httpx.AsyncClient` to ensure correct SSL, proxy, timeouts, and redirects.
+
+Guidance for Copilot:
+- When suggesting `httpx.Client(` or `httpx.AsyncClient(`, include `**get_httpx_client_kwargs()`.
+- If the user omits it, suggest the corrected version or insert a warning comment.
+
+Preferred patterns:
+```python
+import httpx
+from uipath._utils._ssl_context import get_httpx_client_kwargs
+
+client = httpx.Client(**get_httpx_client_kwargs())
+async_client = httpx.AsyncClient(**get_httpx_client_kwargs())
+
+default_client_kwargs = get_httpx_client_kwargs()
+client_kwargs = {
+    **default_client_kwargs,
+    "base_url": base_url,
+    "headers": my_headers,
+}
+client = httpx.Client(**client_kwargs)
+async_client = httpx.AsyncClient(**client_kwargs)
+```
+
+Anti-patterns (avoid):
+```python
+client = httpx.Client()              # ❌ Missing **get_httpx_client_kwargs()
+async_client = httpx.AsyncClient()   # ❌ Missing **get_httpx_client_kwargs()
+```
+
+Warning to insert if correction isn’t applied:
+```python
+# WARNING: Use httpx.Client/AsyncClient with **get_httpx_client_kwargs() for proper SSL/proxy configuration.
+```
+
+Reference:
+- [get_httpx_client_kwargs](https://github.com/UiPath/uipath-python/blob/main/src/uipath/_utils/_ssl_context.py#L37)

.github/workflows/lint.yml

@@ -49,3 +49,6 @@ jobs:
 
       - name: Check formatting
         run: uv run ruff format --check .
+
+      - name: Check httpx.Client() usage
+        run: uv run python scripts/lint_httpx_client.py

pyproject.toml

@@ -18,6 +18,8 @@ dependencies = [
     "openinference-instrumentation-langchain>=0.1.56",
     "jsonschema-pydantic-converter>=0.1.5",
     "jsonpath-ng>=1.7.0",
+    "mcp>=1.24.0",
+    "langchain-mcp-adapters>=0.2.1",
 ]
 
 classifiers = [

samples/simple-remote-mcp-agent/.env.example

@@ -0,0 +1,2 @@
+UIPATH_MCP_SERVER_URL=***
+ANTHROPIC_API_KEY=***

samples/simple-remote-mcp-agent/AGENTS.md

@@ -0,0 +1,21 @@
+# Agent Code Patterns Reference
+
+This document provides practical code patterns for building UiPath coded agents using 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, Output), SDK 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/simple-remote-mcp-agent/CLAUDE.md

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

samples/simple-remote-mcp-agent/README.md

@@ -0,0 +1,71 @@
+# LangGraph Agent with Claude and Tool MCP Servers
+
+This project demonstrates how to create an agent using LangGraph react agent which connects to a Remote MCP Server hosted in UiPath.
+
+## Overview
+
+The agent uses:
+- LangGraph for orchestration
+- Connects to a Remote MCP server
+
+## Architecture
+
+```mermaid
+---
+config:
+  flowchart:
+    curve: linear
+---
+graph TD;
+	__start__([<p>__start__</p>]):::first
+	agent(agent)
+	tools(tools)
+	__end__([<p>__end__</p>]):::last
+	__start__ --> agent;
+	tools --> agent;
+	agent -.-> tools;
+	agent -.-> __end__;
+	classDef default fill:#f2f0ff,line-height:1.2
+	classDef first fill-opacity:0
+	classDef last fill:#bfb6fc
+```
+
+The workflow follows a ReAct pattern:
+1. Query is sent to the agent (Claude)
+2. Agent decides whether to use tools or provide a final answer
+3. If tools are needed, the request is sent to the remote MCP server
+4. Results from tools are sent back to the agent
+5. Process repeats until the agent has enough information to provide a final answer
+
+## Prerequisites
+
+- Python 3.11+
+- `langchain-anthropic`
+- `langchain-mcp-adapters`
+- `langgraph`
+- Anthropic API key set as an environment variable
+
+## Installation
+
+```bash
+uv venv -p 3.11 .venv
+.venv\Scripts\activate
+uv sync
+```
+
+Set your API keys and MCP Remote Server URL as environment variables in .env
+
+```bash
+ANTHROPIC_API_KEY=your_anthropic_api_key
+```
+
+## Debugging
+
+For debugging issues:
+
+1. Check logs for any connection or runtime errors:
+   ```bash
+   uipath run agent --debug '{"messages": [{"type": "human", "content": "What is 2+2"}]}'
+   ```
+
+

samples/simple-remote-mcp-agent/bindings.json

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

samples/simple-remote-mcp-agent/entry-points.json

@@ -0,0 +1,5 @@
+{
+    "$schema": "https://cloud.uipath.com/draft/2024-12/entry-point",
+    "$id": "entry-points.json",
+    "entryPoints": []
+}

samples/simple-remote-mcp-agent/main.py

@@ -0,0 +1,117 @@
+from contextlib import asynccontextmanager
+from datetime import datetime, timezone
+from typing import Sequence
+
+from langchain_core.messages import HumanMessage, SystemMessage
+from langchain_core.tools import BaseTool
+from pydantic import BaseModel, Field
+from uipath.agent.models.agent import AgentMcpResourceConfig, AgentMcpTool
+from uipath.agent.react import AGENT_SYSTEM_PROMPT_TEMPLATE
+
+from uipath_langchain.agent.react import create_agent
+from uipath_langchain.agent.tools import create_mcp_tools
+from uipath_langchain.chat import OpenAIModels, UiPathChat
+
+# LLM Model Configuration
+llm = UiPathChat(
+    model=OpenAIModels.gpt_5_mini_2025_08_07,
+    temperature=0.0,
+    max_tokens=16384,
+)
+
+
+# Input/Output Models
+class AgentInput(BaseModel):
+    pass
+
+
+class AgentOutput(BaseModel):
+    content: str | None = Field(None, description="Output content")
+
+
+# Agent Messages Function
+def create_messages(state: AgentInput) -> Sequence[SystemMessage | HumanMessage]:
+    # Apply system prompt template
+    current_date = datetime.now(timezone.utc).strftime("%Y-%m-%d")
+    system_prompt_content = f"""You are an agentic assistant."""
+    enhanced_system_prompt = (
+        AGENT_SYSTEM_PROMPT_TEMPLATE.replace("{{systemPrompt}}", system_prompt_content)
+        .replace("{{currentDate}}", current_date)
+        .replace("{{agentName}}", "Mr Assistant")
+    )
+
+    return [
+        SystemMessage(content=enhanced_system_prompt),
+        HumanMessage(content=f"""Do me an RPA echo of "asdf"."""),
+    ]
+
+
+mcpTools = [
+    AgentMcpResourceConfig(
+        name="uipath-server",
+        description="a",
+        folderPath="611ca479-1f38-4abc-b2c6-6a61fa002978",
+        slug="uipath-server",
+        availableTools=[],
+        isEnabled=True,
+    ),
+    AgentMcpResourceConfig(
+        name="uipath-server-2",
+        description="a",
+        folderPath="611ca479-1f38-4abc-b2c6-6a61fa002978",
+        slug="uipath-server-2",
+        availableTools=[],
+        isEnabled=True,
+    ),
+    AgentMcpResourceConfig(
+        name="hello-world",
+        description="a",
+        folderPath="611ca479-1f38-4abc-b2c6-6a61fa002978",
+        slug="hello-world",
+        availableTools=[],
+        isEnabled=True,
+    ),
+    AgentMcpResourceConfig(
+        name="mcp-hello-world-24-25",
+        description="a",
+        folderPath="611ca479-1f38-4abc-b2c6-6a61fa002978",
+        slug="mcp-hello-world-24-25",
+        availableTools=[
+            AgentMcpTool(
+                name="add",
+                description="""
+                Add two numbers together.
+                    Args:
+                        a: First number
+                        b: Second number
+
+                    Returns:
+                        Sum of a and b
+                """,
+                inputSchema={
+                    "type": "object",
+                    "properties": {
+                        "a": {"type": "number", "title": "A"},
+                        "b": {"type": "number", "title": "B"},
+                    },
+                    "required": ["a", "b"],
+                },
+            )
+        ],
+        isEnabled=True,
+    ),
+]
+
+all_tools: list[BaseTool] = []
+
+
+@asynccontextmanager
+async def make_graph():
+    async with create_mcp_tools(mcpTools) as tools:
+        yield create_agent(
+            model=llm,
+            tools=tools + all_tools,
+            messages=create_messages,
+            input_schema=AgentInput,
+            output_schema=AgentOutput,
+        )

samples/simple-remote-mcp-agent/pyproject.toml

@@ -0,0 +1,24 @@
+[project]
+name = "simple-remote-mcp-agent"
+version = "0.0.1"
+description = "simple-remote-mcp-agent"
+authors = [{ name = "John Doe", email = "john.doe@myemail.com" }]
+dependencies = [
+    "langchain>=1.1.0",
+    "langchain-anthropic>=1.2.0",
+    "langgraph>=1.0.4",
+    "python-dotenv>=1.0.0",
+    "anthropic>=0.57.1",
+    "langchain-mcp-adapters>=0.1.14",
+    "uipath>=2.2.0, <2.3.0",
+    "uipath-langchain>=0.1.30",
+]
+requires-python = ">=3.11"
+
+[tool.setuptools]
+py-modules = []
+
+[dependency-groups]
+dev = [
+    "uipath-dev>=0.0.5",
+]

samples/simple-remote-mcp-agent/uipath.json

@@ -0,0 +1,14 @@
+{
+  "$schema": "https://cloud.uipath.com/draft/2024-12/uipath",
+  "runtimeOptions": {
+    "isConversational": false
+  },
+  "packOptions": {
+    "fileExtensionsIncluded": [],
+    "filesIncluded": [],
+    "filesExcluded": [],
+    "directoriesExcluded": [],
+    "includeUvLock": true
+  },
+  "functions": {}
+}