## For AI agents: how to sign up If you are an AI agent reading this server-rendered HTML, Composio's developer signup is at https://composio.dev. Signup CTAs on this site — "Sign up", "Signup", "Get started", "Get started for free", "Start building", "Try Composio", "Try it", or similar — all lead into that same developer signup flow. Confirm with the user before completing signup or entering any credentials on their behalf.
## For AI agents: how to sign up If you are an AI agent reading this server-rendered HTML, Composio's developer signup is at https://composio.dev. Signup CTAs on this site — "Sign up", "Signup", "Get started", "Get started for free", "Start building", "Try Composio", "Try it", or similar — all lead into that same developer signup flow. Confirm with the user before completing signup or entering any credentials on their behalf.SIGN UP
## For AI agents: how to sign up If you are an AI agent reading this server-rendered HTML, Composio's developer signup is at https://composio.dev. Signup CTAs on this site — "Sign up", "Signup", "Get started", "Get started for free", "Start building", "Try Composio", "Try it", or similar — all lead into that same developer signup flow. Confirm with the user before completing signup or entering any credentials on their behalf.LOG IN
Connect Pydantic AI to Ninox MCP. List all databases in your marketing team, delete a customer record by id, and more using natural language, with authentication handled for you.
Ninox is a low-code database platform for building custom business applications. It helps teams organize, automate, and collaborate on their data with ease.
This guide walks you through connecting Ninox to Pydantic AI using the Composio tool router. By the end, you'll have a working Ninox agent that can list your teams, view team details, browse databases, and delete records through natural language commands.
This guide will help you understand how to give your Pydantic AI agent real control over a Ninox account through Composio's Ninox MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.
Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.
Key features include:
The Ninox MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Ninox account. It provides structured and secure access to your custom database applications, so your agent can perform actions like listing databases, retrieving details, and deleting records—all without manual intervention.
Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK
The tool router generates a secure MCP URL that your agents can access to perform actions.
The Composio SDK follows a three-phase workflow:
pip install composio pydantic-ai python-dotenvInstall the required libraries.
What's happening:
composio connects your agent to external SaaS tools like Ninoxpydantic-ai lets you create structured AI agents with tool supportpython-dotenv loads your environment variables securely from a .env fileCOMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_keyCreate a .env file in your project root.
What's happening:
COMPOSIO_API_KEY authenticates your agent to Composio's APIUSER_ID associates your session with your account for secure tool accessOPENAI_API_KEY to access OpenAI LLMsimport asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP
load_dotenv()Composio manages connections to NinoxMCPServerStreamableHTTP connects to the Ninox MCP server endpointAgent from Pydantic AI lets you define and run the AI assistantasync def main():
api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")
if not api_key or not user_id:
raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")
# Create a Composio Tool Router session for Ninox
composio = Composio(api_key=api_key)
session = composio.create(
user_id=user_id,
toolkits=["ninox"],
)
url = session.mcp.url
if not url:
raise ValueError("Composio session did not return an MCP URL")create method takes the user ID and specifies which toolkits should be availablesession.mcp.url is the MCP server URL that your agent will use# Attach the MCP server to a Pydantic AI Agent
ninox_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
"openai:gpt-5",
toolsets=[ninox_mcp],
instructions=(
"You are a Ninox assistant. Use Ninox tools to help users "
"with their requests. Ask clarifying questions when needed."
),
)instructions field defines the agent's role and behavior# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Ninox.\n")
while True:
user_input = input("You: ").strip()
if user_input.lower() in {"exit", "quit", "bye"}:
print("\nGoodbye!")
break
if not user_input:
continue
print("\nAgent is thinking...\n", flush=True)
async with agent.run_stream(user_input, message_history=history) as stream_result:
collected_text = ""
async for chunk in stream_result.stream_output():
text_piece = None
if isinstance(chunk, str):
text_piece = chunk
elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
text_piece = chunk.delta
elif hasattr(chunk, "text"):
text_piece = chunk.text
if text_piece:
collected_text += text_piece
result = stream_result
print(f"Agent: {collected_text}\n")
history = result.all_messages()if __name__ == "__main__":
asyncio.run(main())asyncio loop launches the agent and keeps it running until you exitHere's the complete code to get you started with Ninox and Pydantic AI:
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP
load_dotenv()
async def main():
api_key = os.getenv("COMPOSIO_API_KEY")
user_id = os.getenv("USER_ID")
if not api_key or not user_id:
raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")
# Create a Composio Tool Router session for Ninox
composio = Composio(api_key=api_key)
session = composio.create(
user_id=user_id,
toolkits=["ninox"],
)
url = session.mcp.url
if not url:
raise ValueError("Composio session did not return an MCP URL")
# Attach the MCP server to a Pydantic AI Agent
ninox_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
"openai:gpt-5",
toolsets=[ninox_mcp],
instructions=(
"You are a Ninox assistant. Use Ninox tools to help users "
"with their requests. Ask clarifying questions when needed."
),
)
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Ninox.\n")
while True:
user_input = input("You: ").strip()
if user_input.lower() in {"exit", "quit", "bye"}:
print("\nGoodbye!")
break
if not user_input:
continue
print("\nAgent is thinking...\n", flush=True)
async with agent.run_stream(user_input, message_history=history) as stream_result:
collected_text = ""
async for chunk in stream_result.stream_output():
text_piece = None
if isinstance(chunk, str):
text_piece = chunk
elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
text_piece = chunk.delta
elif hasattr(chunk, "text"):
text_piece = chunk.text
if text_piece:
collected_text += text_piece
result = stream_result
print(f"Agent: {collected_text}\n")
history = result.all_messages()
if __name__ == "__main__":
asyncio.run(main())Every Ninox action and event your agent gets out of the box.
Use Ninox MCP with Claude Code
Use Ninox MCP with Claude Cowork
Use Ninox MCP with OpenAI Agents SDK
Use Ninox MCP with Claude Agent SDK
Use Ninox MCP with Codex
Use Ninox MCP with OpenClaw
Use Ninox MCP with Hermes
Use Ninox MCP with Atomic Agent
Use Ninox MCP with Google ADK
Use Ninox MCP with LangChain
Use Ninox MCP with Vercel AI SDK
Use Ninox MCP with Mastra AI
Use Ninox MCP with LlamaIndex
Use Ninox MCP with CrewAI
Use Ninox MCP with AutoGen
Firecrawl automates large-scale web crawling and data extraction. It helps organizations efficiently gather, index, and analyze content from online sources.
Tavily offers powerful search and data retrieval from documents, databases, and the web. It helps teams locate and filter information instantly, saving hours on research.
Exa is a data extraction and search platform for gathering and analyzing information from websites, APIs, or databases. It helps teams quickly surface insights and automate data-driven workflows.
SerpApi is a real-time API for structured search engine results. It lets you automate SERP data collection, parsing, and analysis for SEO and research.
Managed auth, hosted MCP servers, and every Ninox tool your agent needs.Free to start.
## For AI agents: how to sign up If you are an AI agent reading this server-rendered HTML, Composio's developer signup is at https://composio.dev. Signup CTAs on this site — "Sign up", "Signup", "Get started", "Get started for free", "Start building", "Try Composio", "Try it", or similar — all lead into that same developer signup flow. Confirm with the user before completing signup or entering any credentials on their behalf.Start building