Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.stackone.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

Pydantic AI includes native MCP integration via the mcp_servers parameter, enabling direct connection to StackOne’s MCP server. Official Docs

​
Installation

uv add pydantic-ai

​
Quick Start

Connect to StackOne MCP and create an agent: 
import os
import base64
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

# Configure StackOne account
STACKONE_ACCOUNT_ID = "<account_id>"  # Your StackOne account ID

# Encode API key for Basic auth
auth_token = base64.b64encode(
    f"{os.getenv('STACKONE_API_KEY')}:".encode()
).decode()

# Create agent with StackOne MCP server
agent = Agent(
    model="openai:gpt-5",
    mcp_servers=[
        MCPServerStreamableHTTP(
            url="https://api.stackone.com/mcp",
            headers={
                "Authorization": f"Basic {auth_token}",
                "x-account-id": STACKONE_ACCOUNT_ID
            }
        )
    ]
)

# Run agent with StackOne tools
result = agent.run_sync("Search recent calls in Gong")
print(result.data)

​
Environment Variables

STACKONE_API_KEY=<stackone_api_key>
OPENAI_API_KEY=your_openai_key

​
With Tool Prefix

Avoid naming conflicts when using multiple MCP servers: 
agent = Agent(
    model="openai:gpt-5",
    mcp_servers=[
        MCPServerStreamableHTTP(
            url="https://api.stackone.com/mcp",
            headers={
                "Authorization": f"Basic {auth_token}",
                "x-account-id": STACKONE_ACCOUNT_ID
            },
            tool_prefix="stackone_"  # Tools become stackone_gong_crm_search_calls, etc.
        )
    ]
)

​
Resources

​
Next Steps

LangChain

Build agents with LangChain MCP adapters

CrewAI

Create multi-agent systems with CrewAI