How to Use the Ably MCP in Pydantic AI

Q: Can I use Ably to update messages in Pydantic AI?

Use the updatemessage tool for modifications. Since you are using Pydantic AI, the result of this action is automatically checked against your types.

Build type-safe real-time messaging agents using Ably and 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 Ably MCP to Pydantic AI

Create your Vinkius account to connect Ably 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 Ably with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Publish messages with Pydantic AI type safety

Your agent triggers `publish_message` while Pydantic AI validates every response against your models. It prevents bad data from ever hitting your channels. Handle batch operations using `batch_publish` with full runtime validation. You catch schema errors the moment the server returns a result.

Validate channel data in Pydantic AI

Retrieve messages via `get_messages` and let Pydantic AI enforce the structure. If the API returns unexpected fields, your agent fails safely. Check specific message serials with `get_message` to verify content. It ensures your agent only acts on data that matches your defined types.

Manage Ably tokens via Pydantic AI

Revoke access keys securely by calling `revoke_tokens` within your agent flow. This keeps your messaging permissions tight and current. Audit your active channels with `list_channels` to maintain a clean environment. Your agent uses these lists to organize its communication logic.

Setup guide

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

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

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

The MCP Server returns data that Pydantic AI validates at runtime. If the output doesn't match your Pydantic models, the agent stops immediately to prevent errors.

You initialize an MCPToolset with your server URL. Then, pass that toolset into the agent definition to expose the messaging operations.

Yes, the setup supports Streamable HTTP and SSE transports. You run the server externally and point your agent to the endpoint.

Use the `update_message` tool for modifications. Since you are using Pydantic AI, the result of this action is automatically checked against your types.

The server runs in an ephemeral, isolated environment. It only exposes message content and presence strings that you explicitly retrieve through your validated agent code.

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