How to Use the FireHydrant MCP in LangChain

Q: How do I connect the FireHydrant MCP Server to a LangChain agent?

Install the langchain-mcp-adapters package and initialize the MultiServerMCPClient with the Vinkius endpoint. From there, pull the tools via client.gettools() and pass them to your agent constructor to start executing actions like createincident.

Q: Can my LangChain agent automatically update active FireHydrant incidents?

Yes, your agent can monitor external telemetry and use updateincident to modify severity or status. It can also run addincidentnote to post diagnostic logs directly into the incident timeline.

Q: Can I run multi-step incident investigations with FireHydrant?

Yes, you can build chains where the output of listchangeevents is evaluated by the agent to find the root cause, which then triggers addincidentnote to document the suspect deployment.

Spin up LangChain chains that instantly open FireHydrant incidents and route them to the right teams when alerts spike.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FireHydrant MCP to LangChain

Create your Vinkius account to connect FireHydrant 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 FireHydrant with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain incident responses with LangChain and this MCP Server

During an active outage, manual steps waste minutes. This MCP Server lets your LangChain agent run multi-step triage pipelines. When a monitoring alert fires, the agent can call `create_incident` to open the ticket, pull service context with `get_service`, and match the failure to the correct on-call group using `list_teams` without human intervention. LangSmith tracks every step of this sequence. You can inspect the exact inputs passed to `list_runbooks` or the outputs returned from `get_incident` to verify that your automated triage logic is making the right decisions before paging a human.

Automate on-call triage and runbook attachment

Your LangChain agents can dynamically adapt their actions based on real-time incident updates. If an agent detects a spike in database latency, it can execute `list_change_events` to find recent deployments and immediately run `update_incident` to raise the severity level. The agent then uses `list_runbooks` to find the exact recovery steps for that database service and attaches them. This keeps your responders from digging through wikis when the site is down.

Inject live incident data into your agent chains

Accessing live operational data directly from your LangChain runtimes is now possible with this MCP server. Instead of hardcoding alert routing, the agent queries `list_services` and `get_team` to find who owns the broken code. It then writes updates to the incident timeline via `add_incident_note`, keeping stakeholders informed in real time. Keeping your communication loop tight and documented becomes automatic.

Setup guide

Set up FireHydrant 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 FireHydrant 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({
    "firehydrant-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 FireHydrant 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 FireHydrant. 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 FireHydrant 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 FireHydrant MCP in LangChain

Install the `langchain-mcp-adapters` package and initialize the `MultiServerMCPClient` with the Vinkius endpoint. From there, pull the tools via `client.get_tools()` and pass them to your agent constructor to start executing actions like `create_incident`.

Yes, your agent can monitor external telemetry and use `update_incident` to modify severity or status. It can also run `add_incident_note` to post diagnostic logs directly into the incident timeline.

LangSmith records every tool call made by the agent, showing the exact payloads sent to `get_service` or `list_runbooks`. If an agent fails to route an incident, you can pinpoint whether the error lies in the agent's reasoning or the API response.

Yes, you can build chains where the output of `list_change_events` is evaluated by the agent to find the root cause, which then triggers `add_incident_note` to document the suspect deployment.

This server accesses operational metadata including active incidents, service maps, and responder schedules. All data stays within the ephemeral V8 sandbox, and your API keys are never exposed to the LLM or stored on disk.

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