Hookdeck MCP Server for Pydantic AIGive Pydantic AI instant access to 52 tools to Cancel Event, Count Connections, Count Sources, and more

Name: Hookdeck
Price: 29 USD
Availability: InStock
Rating: 4.9 (1 reviews)
Author: Vinkius

GDPR Free for Subscribers

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

Ask AI about this MCP Server for Pydantic AI

Open in ChatGPT Open in Claude Open in Perplexity

The Hookdeck MCP Server for Pydantic AI is a standout in the Developer Tools category — giving your AI agent 52 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

+ other MCP clients

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 Hookdeck "
            "(52 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Hookdeck?"
    )
    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 Hookdeck MCP Server

Connect your Hookdeck account to any AI agent to orchestrate your webhook infrastructure through natural conversation. Hookdeck provides the reliability layer for your event-driven architecture, and this server puts that power in your chat interface.

Pydantic AI validates every Hookdeck tool response against typed schemas, catching data inconsistencies at build time. Connect 52 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

Connection Management — List, create, and update connections that route webhooks from sources to destinations.
Traffic Control — Instantly pause or resume event routing for specific connections to manage maintenance windows or outages.
Source Monitoring — Retrieve and count your webhook sources to understand where your incoming data originates.
Lifecycle Operations — Enable or disable connections and manage their rules via JSON payloads without leaving your workflow.
Deep Inspection — Fetch specific metadata for any connection or source using unique IDs to debug routing issues.

The Hookdeck MCP Server exposes 52 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 52 Hookdeck tools available for Pydantic AI

When Pydantic AI connects to Hookdeck through Vinkius, your AI agent gets direct access to every tool listed below — spanning webhooks, event-driven, api-integration, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

cancel

Cancel event on Hookdeck

Cancel scheduled retries for an event

count

Count connections on Hookdeck

Count total connections

count

Count sources on Hookdeck

Count total sources

create

Create bookmark on Hookdeck

Create a new bookmark

create

Create connection on Hookdeck

Create a connection

create

Create destination on Hookdeck

Create a new destination

create

Create issue trigger on Hookdeck

Create a new issue trigger

create

Create source on Hookdeck

Create a new source

create

Create transformation on Hookdeck

Create a new transformation

delete

Delete bookmark on Hookdeck

Remove a bookmark

delete

Delete connection on Hookdeck

Permanently delete a connection

delete

Delete destination on Hookdeck

Delete a destination

delete

Delete issue trigger on Hookdeck

Delete an issue trigger

delete

Delete source on Hookdeck

Delete a source

disable

Disable connection on Hookdeck

Disable a connection

disable

Disable source on Hookdeck

Disable a source

enable

Enable connection on Hookdeck

Enable a disabled connection

enable

Enable source on Hookdeck

Enable a source

get

Get attempt on Hookdeck

Retrieve a specific attempt

get

Get connection on Hookdeck

Retrieve a specific connection

get

Get destination on Hookdeck

Retrieve a specific destination

get

Get event on Hookdeck

Retrieve a specific event

get

Get issue trigger on Hookdeck

Retrieve a specific issue trigger

get

Get metrics attempts on Hookdeck

Delivery attempt metrics

get

Get metrics events on Hookdeck

Event processing statistics

get

Get metrics queue depth on Hookdeck

Current queue depth per destination

get

Get metrics requests on Hookdeck

Request volume metrics

get

Get metrics transformations on Hookdeck

Transformation execution performance

get

Get request on Hookdeck

Retrieve a specific request

get

Get source on Hookdeck

Retrieve a specific source

get

Get transformation on Hookdeck

Retrieve a specific transformation

list

List attempts on Hookdeck

Retrieve a list of delivery attempts

list

List bookmarks on Hookdeck

Retrieve a list of bookmarks

list

List connections on Hookdeck

Retrieve a list of connections

list

List destinations on Hookdeck

Retrieve a list of destinations

list

List events on Hookdeck

Retrieve a list of events

list

List issue triggers on Hookdeck

Retrieve a list of issue triggers

list

List requests on Hookdeck

Retrieve a list of requests

list

List sources on Hookdeck

Retrieve a list of sources

list

List transformations on Hookdeck

Retrieve a list of transformations

pause

Pause connection on Hookdeck

Pause event routing for a connection

retry

Retry event on Hookdeck

Manually retry a failed event

retry

Retry request on Hookdeck

Retry a rejected request

test

Test transformation on Hookdeck

Test transformation code against a payload

trigger

Trigger bookmark on Hookdeck

Replay the bookmarked request

unpause

Unpause connection on Hookdeck

Resume event routing for a connection

update

Update connection on Hookdeck

Update a connection rules or name

update

Update destination on Hookdeck

Update destination config (URL, rate limit, etc.)

update

Update issue trigger on Hookdeck

Update an issue trigger

update

Update source on Hookdeck

Update a source

update

Update transformation on Hookdeck

Update transformation code

upsert

Upsert connection on Hookdeck

Create or update a connection by name

Connect Hookdeck to Pydantic AI via MCP

Follow these steps to wire Hookdeck into Pydantic AI. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

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 52 tools from Hookdeck with type-safe schemas

Why Use Pydantic AI with the Hookdeck MCP Server

Pydantic AI provides unique advantages when paired with Hookdeck 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 Hookdeck integration code

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

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

Hookdeck + Pydantic AI Use Cases

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

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

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

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

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

Example Prompts for Hookdeck in Pydantic AI

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

"List all my current Hookdeck connections."

"Pause the connection with ID conn_456 immediately."

"How many webhook sources do I have?"

Troubleshooting Hookdeck MCP Server with Pydantic AI

Common issues when connecting Hookdeck to Pydantic AI through Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Hookdeck + Pydantic AI FAQ

Common questions about integrating Hookdeck 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 Hookdeck MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.