How to Use the Honeycomb MCP in Claude Code

Q: Can I run Honeycomb queries in a non-interactive shell with Claude Code?

Yes. You can script Claude Code to execute runquery and poll getqueryresult as part of a headless pipeline, outputting raw telemetry data directly to stdout.

Q: How does Claude Code authenticate with the Honeycomb MCP server?

You configure the Vinkius endpoint token in your .claude.json file. Claude Code uses this single token to securely access all 12 tools on the server.

Q: Can Claude Code write markers to Honeycomb during CI/CD runs?

Yes, Claude Code can invoke createmarker through the MCP server in automated scripts to annotate your Honeycomb dataset timeline when a build succeeds or a deployment completes.

Q: How do I check dataset columns in Claude Code?

Run Claude Code and ask it to list fields. It will execute listdatasetcolumns for your specific dataset slug and output the schema directly in your terminal.

Query Honeycomb datasets and manage markers directly from your terminal using Claude Code headless commands.

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 Claude Code

Create your Vinkius account to connect Honeycomb to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Terminal-Driven Honeycomb Queries via Claude Code

`run_query` triggers query executions directly from your CLI environment without opening a browser. Claude Code sends the query JSON to Honeycomb and polls `get_query_result` to pipe the raw JSON output straight to your terminal. The tool uses `list_datasets` to fetch valid slugs, allowing you to quickly target different environments. You can easily pipe these telemetry outputs into other CLI tools or save them to local diagnostic logs.

CLI Marker Management

`create_marker` injects deployment annotations directly into your Honeycomb datasets from your active terminal session. Claude Code automatically extracts your current git branch or tag to populate the marker message. You can run `list_markers` to display recent timeline annotations directly in your shell. This helps SREs correlate terminal actions with telemetry events without context switching to the Honeycomb web UI.

Inspect Triggers and Board Schemas via MCP Server

`list_triggers` lists all active alerts for your service datasets right inside your terminal session using the MCP server. Claude Code inspects these alerts and uses `list_dataset_columns` to check which fields are being monitored. It also runs `list_honeycomb_boards` to output team dashboard configurations. This lets you inspect query layouts and team metadata using `get_team_details` without leaving your SSH session.

Setup guide

Set up Honeycomb MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see honeycomb-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Honeycomb transactions." It will automatically discover and invoke the available Honeycomb tools.

Terminal

claude mcp add --transport http honeycomb-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Honeycomb MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "honeycomb-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

Yes. You can script Claude Code to execute `run_query` and poll `get_query_result` as part of a headless pipeline, outputting raw telemetry data directly to stdout.

You configure the Vinkius endpoint token in your `~.claude.json` file. Claude Code uses this single token to securely access all 12 tools on the server.

Yes, Claude Code can invoke `create_marker` through the MCP server in automated scripts to annotate your Honeycomb dataset timeline when a build succeeds or a deployment completes.

Run Claude Code and ask it to list fields. It will execute `list_dataset_columns` for your specific dataset slug and output the schema directly in your terminal.

All query payloads, schema details, and trigger definitions pass through Vinkius's ephemeral, zero-trust V8 sandbox running the MCP server. Your credentials and raw telemetry are never cached 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