How to Use the Chainlit MCP in Pydantic AI

Q: How do I set up Chainlit with Pydantic AI?

Install pydantic-ai-slimmcp first. Initialize an MCPToolset with your Vinkius HTTP endpoint, then pass it as toolsets=toolset to your Agent instance.

Connect Chainlit to Pydantic AI to enforce strict runtime validation on your LLM observability metrics and chat topologies.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Chainlit MCP to Pydantic AI

Create your Vinkius account to connect Chainlit 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 Chainlit with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Chainlit stats with this MCP Server

Type-safe agents refuse to guess what an API returns. When your agent calls `list_projects` to find globally configured Chainlit Cloud environments, Pydantic validates the response structure instantly. If the API changes, the agent fails loudly with a validation error. Tracking resource consumption demands exact numbers, not hallucinated fields. The agent uses `get_stats` to pull traffic boundaries for native projects. Every integer and string gets checked against your Pydantic models at runtime, guaranteeing correct data before your agent makes a decision.

Extract exact conversational payloads safely

Navigating complex chat topologies requires strict data contracts. Your agent runs `list_threads` to identify user interaction boundaries inside a deployed project. It knows exactly how many threads exist because the MCP Server output is strictly typed. Pulling the full history happens through `get_thread`. The agent receives the exact payload for a specific conversational thread. There is no silent corruption here; if a node topology is missing a required field, the framework catches it immediately.

Audit raw prompts and user review ratings

Correctness matters more than speed when evaluating programmatic interactions. By calling `list_steps`, the agent retrieves raw prompts and generations inside a single thread. It parses the explicit interaction steps into clean, validated Python objects. Assessing conversational accuracy requires reliable metrics. The agent queries `list_feedbacks` to list absolute user review ratings across deployments. You get a model-agnostic workflow that works perfectly whether you use OpenAI, Anthropic, or local models.

Setup guide

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

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

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

Install pydantic-ai-slim[mcp] first. Initialize an MCPToolset with your Vinkius HTTP endpoint, then pass it as toolsets=[toolset] to your Agent instance.

Yes, the framework validates every response at runtime. If the get_thread tool returns an unexpected node topology, the agent throws a validation error immediately instead of hallucinating data.

The framework is completely model-agnostic. You can route the programmatic interaction steps pulled from list_steps to any local or cloud-based LLM that supports function calling.

No, that class is deprecated. You should use the unified MCPToolset approach to connect to the external endpoint over Streamable HTTP or SSE transports.

Vinkius hosts the tools in a zero-trust V8 Isolate Sandbox. When your agent pulls explicit interaction steps via list_steps, the ephemeral environment ensures that sensitive prompt data is never cached or exposed to other tenants.

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