Can I remove a participant from a live session through the agent?

Yes. The `remove_peer` tool allows your AI agent to disconnect any participant from an active session using their peer ID. You can also provide a custom reason for the removal, which will be logged in your session history.

How do I check if a video room is currently active?

Use the `list_sessions` tool and filter by the specific room ID and status 'active'. Your agent will return any ongoing sessions for that room along with the number of participants currently joined.

Can I see all cloud recordings for a specific room?

Absolutely. Use the `list_recordings` tool and provide the room ID. Your agent will retrieve all recordings associated with that room, showing their status and technical metadata for auditing purposes.

100ms MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: 100ms
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect 100ms through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to 100ms "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in 100ms?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About 100ms MCP Server

Connect your 100ms account to any AI agent and manage your live video infrastructure through natural conversation.

Pydantic AI validates every 100ms tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Room Management — List all virtual rooms, retrieve deep technical metadata, and create new rooms with specific templates and descriptions
Session Monitoring — Monitor active or completed video sessions in real-time and retrieve session history across your organization
Participant Governance — List all peers (participants) currently in a session and retrieve their unique IDs and roles
Peer Control — Remotely remove or kick participants from active sessions with custom reasons directly from your agent
Recording Discovery — List and browse cloud recordings, filtered by room or status (completed, failed, or processing)
Operational Insights — Quickly find unique room, session, and peer IDs required for automated video workflows
Scalable Infrastructure — Verify your live video configurations and template settings through automated metadata retrieval

The 100ms MCP Server exposes 9 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect 100ms to Pydantic AI via MCP

Follow these steps to integrate the 100ms MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 9 tools from 100ms with type-safe schemas

Why Use Pydantic AI with the 100ms MCP Server

Pydantic AI provides unique advantages when paired with 100ms through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your 100ms integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your 100ms connection logic from agent behavior for testable, maintainable code

100ms + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the 100ms MCP Server delivers measurable value.

Type-safe data pipelines: query 100ms with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple 100ms tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query 100ms and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock 100ms responses and write comprehensive agent tests

100ms MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect 100ms to Pydantic AI via MCP:

create_room

Use this when the user asks to start or host a new meeting space. Create a new video room

get_room

Requires the unique room ID. Get the configuration and details of a specific video room

get_session

Get the details and metadata of a specific video session

list_peers

Requires the session ID. List all participants currently inside an active video session

list_recordings

Can optionally filter by room ID or the status of the recording. List cloud recordings of video rooms

list_rooms

Use this to find a room ID. List all video rooms in the 100ms account

list_sessions

You can filter by room ID or status. Use this to find who attended past meetings. List active or past video sessions

remove_peer

Requires the session ID and the peer ID. Kick or remove a specific participant from an active video session

update_room

Requires the room ID. Update the settings of an existing video room

Example Prompts for 100ms in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with 100ms immediately.

"List all my video rooms in 100ms."

"Are there any active sessions for the 'Town Hall' room right now?"

"Remove participant 'peer-123' from the session 'sess-abc' for 'violating community guidelines'."

Troubleshooting 100ms MCP Server with Pydantic AI

Common issues when connecting 100ms to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

100ms + Pydantic AI FAQ

Common questions about integrating 100ms MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your 100ms MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.