How to Use the Deno Deploy MCP in Pydantic AI

Type-safe Deno Deploy management with Pydantic AI. Catch bad deployment configs before they hit production.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Deno Deploy MCP to Pydantic AI

Create your Vinkius account to connect Deno Deploy 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 Deno Deploy with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Validation for Deno Deploy MCP Server

Calling `create_app` through Pydantic AI guarantees your infrastructure payload matches the exact schema. When your agent makes a request, the framework validates the response at runtime. If the API changes or returns a missing field, the script fails loudly instead of silently corrupting your state. You know exactly what data you are getting back. Fetching details via `get_app` guarantees a matching dictionary. We built this integration to prioritize correctness over everything else.

Manage Revisions Safely

Finding the last stable build requires `list_revisions` to return exact strings. Rolling back a broken site demands precise revision IDs. Because Pydantic enforces the schema, the agent never hallucinates a nonexistent identifier. Once it identifies the correct target, it triggers `create_project_deployment` to fix the site. Passing the unified MCPToolset to your Agent constructor handles the wire protocol to the MCP server. You just provide the Vinkius HTTP URL and let it run.

Type-Checked Environment Layers

Defining shared variables with `create_layer` prevents fragile secret management across projects. Your system calls the API to define shared values. Pydantic ensures the payload matches the exact key-value structure required by the endpoint. Updating those values happens through `update_layer`. You can swap out the underlying LLM anytime since the framework is model-agnostic. The server runs externally on our managed infrastructure so your local code stays clean.

Setup guide

Set up Deno Deploy 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": {
        "deno-deploy-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Run pip install for the slim package with the MCP extra. Then initialize MCPToolset with your Vinkius endpoint URL.

Every single API return passes through Pydantic models. A malformed response from `get_revision` triggers an immediate runtime exception.

The framework supports Streamable HTTP and SSE. Just pass the URL string directly into the toolset constructor.

The framework is completely model-agnostic. You manage edge deployments using Anthropic, OpenAI, or a local Llama instance.

Vinkius proxies your requests through an isolated container that holds zero persistent state. Your API keys, layer configurations, and organization IDs are processed in memory and wiped immediately after the HTTP response completes.

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