How to Use the 100ms MCP in Pydantic AI

Q: How do I initialize the 100ms MCP Server in Pydantic AI?

Install the pydantic-ai-slimmcp package to get started. You initialize the connection using the unified MCPToolset with your HTTP endpoint and pass it into your Agent's toolsets array.

Q: How do I list 100ms recordings safely with Pydantic AI?

The agent calls listrecordings and maps the response directly to your defined schema. You can filter by room ID or status, and the framework guarantees the returned recording objects match your types.

Manage 100ms video rooms and live sessions with absolute type safety using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 100ms MCP to Pydantic AI

Create your Vinkius account to connect 100ms 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 100ms with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate active session data at runtime

Your agent pulls real-time meeting information and guarantees the structure matches your exact specifications. When it calls `get_session` to check a live video call, Pydantic AI validates every returned field against your strict data models. Silent data corruption stops immediately. If the API returns a malformed timestamp or missing metadata, the system fails loudly with a validation error rather than passing hallucinated data to your downstream systems.

Manage participants with zero hallucinations

You can build automated moderation tools that never kick the wrong person. The agent queries `list_peers` to map the current active participants, forcing the output into a typed array before taking any action. You eliminate the risk of an LLM guessing a user ID. The agent only executes `remove_peer` when it holds a strictly validated peer ID, ensuring perfect accuracy during live event moderation.

Provision rooms with strict schemas

Your infrastructure agent creates new video spaces exactly as defined in your code. It triggers `create_room` and immediately verifies the resulting room ID and configuration through `get_room`. You stop dealing with misconfigured meeting spaces. The agent uses `update_room` to enforce specific settings, and Pydantic catches any schema mismatches before the room link ever reaches a user.

Setup guide

Set up 100ms 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": {
        "100ms-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to 100ms tools.",
)

result = await agent.run("List recent 100ms 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 100ms. 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 100ms 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 100ms MCP in Pydantic AI

Install the pydantic-ai-slim[mcp] package to get started. You initialize the connection using the unified MCPToolset with your HTTP endpoint and pass it into your Agent's toolsets array.

Yes, it fully supports Server-Sent Events alongside Streamable HTTP. Just make sure your external server is running and accessible before you initialize the toolset.

The agent calls `list_recordings` and maps the response directly to your defined schema. You can filter by room ID or status, and the framework guarantees the returned recording objects match your types.

It handles historical attendance tracking perfectly. The agent uses `list_sessions` to pull the records and validates the participant arrays so you never get hallucinated attendee lists.

Your meeting recordings and live peer lists never leak into training data. The server executes all operations inside a zero-trust sandbox, processing your video infrastructure queries dynamically without storing your private room keys.

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