How to Use the Hookdeck MCP in LangChain

Q: Can LangChain automatically retry failed Hookdeck webhooks?

Yes. Your agent monitors failed deliveries and calls retryevent or retryrequest. You just prompt the agent to watch for specific error codes before triggering the retry.

Wire up your webhook infrastructure directly into LangChain agents to trace, route, and debug events across your entire pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hookdeck MCP to LangChain

Create your Vinkius account to connect Hookdeck to LangChain 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 Hookdeck with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route webhooks through your LangChain MCP Server

The Hookdeck MCP Server exposes your exact connection topology to your agent. You use `create_connection` and `create_source` to set up new ingestion endpoints on the fly. When a new service spins up, your ReAct agent provisions the routing logic without human intervention. The real kicker is how this fits into a chain. You pull the current state with `list_connections`, decide if a route needs pausing, and execute `pause_connection` in one trace. LangSmith logs the exact inputs and outputs so you know why the agent choked off the traffic.

Debug failed payloads automatically

Your agent uses `get_attempt` and `get_event` to pull the raw HTTP headers and body of failed webhook deliveries. It reads the exact reason a destination rejected the payload. No more guessing why the pipe broke. Once the agent identifies the bad payload, it tests a fix using `test_transformation`. If the mutated payload works, the chain moves forward and fires `retry_event` to push the backlog through.

Monitor queue depth and metrics

You pull live telemetry directly into your reasoning loop using `get_metrics_queue_depth` and `get_metrics_attempts`. If the agent sees a massive spike in pending deliveries, it knows the downstream service is drowning. Instead of waking you up at 3 AM, the agent triggers `disable_connection` to stop the bleeding. It acts on hard numbers, not guesses, keeping your destination servers from falling over completely.

Setup guide

Set up Hookdeck MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Hookdeck tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "hookdeck-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Hookdeck transactions"
    })
    print(result["messages"][-1].content)

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 Hookdeck. 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 Hookdeck 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 Hookdeck MCP in LangChain

Install the langchain-mcp-adapters package. Pass your Hookdeck MCP Server URL to MultiServerMCPClient and feed the tools into your ReAct agent.

Yes. Your agent monitors failed deliveries and calls `retry_event` or `retry_request`. You just prompt the agent to watch for specific error codes before triggering the retry.

Writing custom API wrappers takes days and breaks when the spec changes. The MCP Server gives your agent 52 native tools instantly, letting you focus on the reasoning logic instead of the boilerplate.

The tools operate on specific IDs. You write a chain that iterates over `list_events` and calls `retry_event` one by one.

Your LangChain agent processes raw webhook payloads and HTTP headers locally. Vinkius runs the server in an ephemeral V8 Isolate Sandbox, ensuring no event data leaks across sessions or persists after the connection drops.

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