How to Use the Cody AI MCP in Pydantic AI

Q: How do I initialize the Cody AI toolset in Pydantic AI?

Install the library with the mcp extra, then instantiate MCPToolset with your Vinkius HTTP endpoint. Pass this toolset instance inside the toolsets list when initializing your Agent.

Build type-safe customer support pipelines with Cody AI and Pydantic AI runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cody AI MCP to Pydantic AI

Create your Vinkius account to connect Cody AI to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Cody AI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe bot management with Pydantic AI

Stop silent API errors from breaking your support flows. When your agent calls `list_bots` or `get_bot_details`, this framework validates the JSON payload against strict schemas before your code ever runs. If Cody returns an unexpected field or missing parameter, the agent raises a validation error immediately. This gives you absolute confidence that your customer-facing bots are behaving exactly as expected.

Validated document tracking and imports

Importing files shouldn't be a guessing game. Use `import_webpage` to add fresh docs to your knowledge base, and let the framework validate the structural response to ensure the import was accepted. Your agent can then poll `get_document_status` to verify when the processing completes. Because the status fields are strictly typed, your code won't break on unexpected API status codes.

Secure conversation state handling via MCP Server

Manage support sessions without worrying about malformed history logs. The `list_messages` and `list_conversations` tools return structured data that fits perfectly into your custom Pydantic schemas over the MCP connection. When sending prompts with `send_message`, the input parameters are validated locally first. This prevents waste of API credits on malformed requests before they even leave your server.

Setup guide

Set up Cody AI MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "cody-ai-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Cody AI tools.",
)

result = await agent.run("List recent Cody AI transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cody AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Cody AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Cody AI MCP in Pydantic AI

Install the library with the mcp extra, then instantiate `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset instance inside the `toolsets` list when initializing your Agent.

The framework will raise a validation error instantly instead of passing dirty data to your model. This ensures your agent never processes corrupt bot details or malformed conversation histories.

Yes, you can connect using either Streamable HTTP or Server-Sent Events (SSE). The unified `MCPToolset` class handles the underlying connection transport automatically based on your endpoint configuration.

Yes, the framework is completely model-agnostic. You can bind the Cody tools to local models or other commercial API providers while keeping your runtime validation active.

Your raw folder names and document metadata are processed locally within your application's memory space during validation. Vinkius acts as a zero-trust proxy, meaning your directory structure is never stored or cached on intermediate servers.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript