How to Use the Coze MCP in Pydantic AI

Build type-safe Coze integrations using Pydantic AI to validate bot responses and dataset schemas at runtime via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coze MCP to Pydantic AI

Create your Vinkius account to connect Coze 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 Coze with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe bot management via Pydantic AI

Stop worrying about silent API failures or corrupted payloads in your conversational pipelines. When your Pydantic AI agent calls `create_chat` or `get_conversation_history`, the incoming Coze data is strictly validated against strict Python type models before your code ever runs. If a Coze bot returns unexpected fields or missing data, Pydantic AI raises a validation error immediately. This keeps your production systems predictable and prevents bad data from cascading through your application.

Validate knowledge base updates at runtime

Uploading bad data can break your retrieval pipelines. This MCP Server lets your Pydantic AI agent inspect active datasets via `list_datasets` and upload documents using `upload_document` with strict structural validation. By defining Pydantic models for your source text, you ensure that only clean, well-formed data gets sent to Coze storage. If the data doesn't fit the schema, the upload fails inside Pydantic AI before hitting the external API.

Automate workspace discovery without silent errors

Dynamically locating resources requires absolute precision. Your Pydantic AI agent uses `list_workspaces` and `list_bots` to find target environments, parsing the results into typed Python objects. This eliminates runtime guessing games. Your Pydantic AI agent knows exactly what bots are published via `publish_bot` because every Coze response is checked against strict type schemas, preventing silent failures.

Setup guide

Set up Coze 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": {
        "coze-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Coze 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 Coze. 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 Coze 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 Coze MCP in Pydantic AI

Install pydantic-ai-slim with the mcp extra. Use the unified MCPToolset class pointing to your Vinkius HTTP endpoint, and pass it to your Agent constructor to instantly expose tools like `create_chat`.

The framework will throw a validation error. This prevents your agent from processing corrupt chat histories from `get_conversation_history` or acting on invalid bot configurations.

No, this server uses standard HTTP/SSE transports for tool execution. Tools like `create_chat` return complete, validated JSON payloads that your agent can safely parse into structured models.

Use the Streamable HTTP or SSE transport options. The deprecated MCPServerHTTP class should be avoided in favor of the unified MCPToolset approach.

Vinkius executes all MCP tool calls in isolated, zero-trust V8 sandboxes. Your workspace IDs, bot lists, and token data are never written to persistent disk and are completely purged from memory after each tool call.

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