How to Use the Honeycomb MCP in LangChain

Q: How do I handle complex query specs?

Use createqueryspecification first. This returns an ID that you then pass to runquery to keep your chain logic clean and modular.

Chain your observability tasks in LangChain with this MCP Server for direct access to your Honeycomb telemetry data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Honeycomb MCP to LangChain

Create your Vinkius account to connect Honeycomb 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 Honeycomb with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate your telemetry pipeline in LangChain

Connect your agents to Honeycomb to pull live data without leaving your chain. Use `list_datasets` to grab your slugs, then fire off `run_query` to get the raw numbers your agent needs to decide what happens next. You build the flow. The agent takes the output from one tool and feeds it into the next, ensuring your observability logic stays inside your execution chain.

Manage deployment markers programmatically

Stop jumping between tabs to annotate your timeline. You can call `create_marker` directly from your agentic workflow to tag deployments or maintenance windows as they occur. Everything stays in sync. By passing your metadata as a JSON string in `body_json`, you ensure the entire team sees exactly what changed and when.

Query your boards and triggers

Your agent can now audit your own alerting infrastructure. Use `list_honeycomb_boards` to find the right dashboard and `list_triggers` to verify your current alert thresholds. It removes the guesswork. When a service degrades, the agent checks the actual board state before deciding if a manual intervention is required.

Setup guide

Set up Honeycomb 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 Honeycomb 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({
    "honeycomb-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 Honeycomb 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 Honeycomb. 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 Honeycomb 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 Honeycomb MCP in LangChain

It gives your agent direct access to your telemetry. Your chain calls `run_query` to fetch trace data and then interprets the results to identify the root cause.

Yes. You can write scripts that monitor your triggers. If an anomaly appears, the agent can use `create_marker` to alert the team in the UI.

Yes. This MCP server acts as a bridge. It only accesses the specific dataset columns you query and keeps your API key local to the server environment.

Use `create_query_specification` first. This returns an ID that you then pass to `run_query` to keep your chain logic clean and modular.

The server returns an error. You should configure your agent to catch these exceptions and retry the `get_query_result` call.

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