How to Use the Flock MCP in Pydantic AI

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

Install the slim package with MCP support and instantiate MCPToolset with your Vinkius HTTP endpoint. Pass this toolset to your Agent using the toolsets argument.

Q: How does the agent retrieve public channel lists?

The agent calls channelslistpublic to fetch all active public channels. It then uses channelsgetinfo to parse descriptions and verify where to route communications.

Run type-safe Pydantic AI agents that validate every Flock message payload and directory lookup at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flock MCP to Pydantic AI

Create your Vinkius account to connect Flock 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 Flock with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce type-safe FlockML delivery via Pydantic AI

The `chat_send_message` tool delivers highly formatted messages using FlockML syntax directly into active channels. Pydantic AI validates the structure of these payloads before transmission, preventing malformed XML from breaking your team's chat UI. If the agent attempts to construct an invalid tag, the framework catches the validation error instantly. This prevents broken layouts from ever reaching your production channels.

Validate private group queries using this MCP Server

The `groups_list_private` tool returns strict arrays of routing UUIDs for your private channels. Using this MCP integration with Pydantic AI guarantees that these IDs match your internal schemas before your agent executes any actions. The agent then runs `groups_get_info` to inspect private credentials. If the returned JSON doesn't match your expected model, the execution halts safely rather than failing silently.

Audit group memberships with strict type checks

The `groups_list_members` tool extracts the exact UUIDs of users belonging to a specific private group. Your agent uses this list to verify that only authorized team members are present before sharing sensitive data. This verification step prevents data leaks by ensuring the recipient list strictly conforms to your organization's security models. You get complete assurance that your automated reports only reach the intended audience.

Setup guide

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

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

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

Install the slim package with MCP support and instantiate `MCPToolset` with your Vinkius HTTP endpoint. Pass this toolset to your Agent using the `toolsets` argument.

The framework raises a validation error immediately. This ensures your agent never processes corrupt metadata or hallucinated fields returned by the `users_get_metadata` tool.

Yes, the framework is model-agnostic. You can use OpenAI, Anthropic, or local models to run tools like `roster_list_directory` without changing your toolset setup.

The agent calls `channels_list_public` to fetch all active public channels. It then uses `channels_get_info` to parse descriptions and verify where to route communications.

Your Flock channel descriptions and user profiles are processed entirely in memory within an isolated V8 sandbox. No data is stored or logged on the Vinkius hosting infrastructure.

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