# Honeycomb MCP

> Let your agent query Honeycomb traces and telemetry to investigate latency and errors, and create Boards, Triggers and SLOs.

Honeycomb's own hosted MCP server. It lets your agent query, explore and iterate on your Honeycomb telemetry the way you do in Honeycomb's UI: running queries, following traces, finding outliers with BubbleUp, and capturing what it finds on Boards.

What you can do with it
- Investigate and diagnose latency or error spikes, starting from a Trigger or a time window
- Run queries, fetch earlier results, find saved queries and find columns by what they mean
- Follow a request through your system with traces and spans, and run BubbleUp to see what sets a subset apart
- See the service map (Enterprise plan) and anomaly detection profiles
- Create and update Boards, Triggers, SLOs and notification recipients
- Translate PromQL or Datadog queries, monitors and Grafana dashboards into Honeycomb queries, Triggers and Boards
- Start or continue Canvas investigations, and analyze telemetry from AI agents that emit OpenTelemetry gen_ai attributes, Claude Code included
- Look up OpenTelemetry semantic conventions, with your team's own attribute descriptions

How it connects
It's hosted at https://mcp.honeycomb.io/mcp for US teams; EU teams connect to https://mcp.eu1.honeycomb.io/mcp instead. Sign in with Honeycomb (OAuth) the first time your agent uses it. For autonomous agents that can't sign in interactively, a team owner can create a Management API key with the Model Context Protocol and Environments scopes and send it as a Bearer Authorization header. Honeycomb documents setup for ChatGPT, Claude, Claude Code, Codex, Cursor, GitHub Copilot, VS Code, Amazon Q and Auggie.

Good to know
- Your Honeycomb team needs Honeycomb Intelligence turned on.
- Most tools only read. Write tools (Boards, Triggers, SLOs, recipients and Canvas) need write access, which you grant at sign-in or on the API key.
- The X-MCP-Toolset header (all, query or canvas) limits which tools your agent loads.
- It also brings prompts: /honeycomb-onboarding helps you get data into Honeycomb, and /honeycomb-learning gives a guided tour of your workspace.

- Type: Plugin
- Made by: Honeycomb
- Category: Cloud & DevOps
- Formats: Remote MCP
- Version: 1.0.0
- Website: https://docs.honeycomb.io/integrations/mcp
- Page: https://pluginboard.ai/plugins/honeycomb-mcp

## Works with

- ChatGPT
- Claude
- Muse
- Grok Bot
- Gemini
- Grok
- GitHub Copilot
- Cursor
- Claude Code
- Codex
- Antigravity
- Gemini CLI
- Replit
- OpenClaw
- OpenCode
- Hermes Agent

## Install

### ChatGPT

In ChatGPT on the web: Plugins → + → Add custom MCP server, then paste https://mcp.honeycomb.io/mcp under Connection. Business and Enterprise plans; Pro can add read-only servers.

### Claude

In Claude (web or desktop): Customize → Connectors → Add custom connector, then paste https://mcp.honeycomb.io/mcp

### Muse

In Muse: In a Muse chat, ask it to create a custom connector for the MCP server at https://mcp.honeycomb.io/mcp. Then tap Connect on the card it shows and sign in, or add your key.

### Grok Bot

In Grok Bot: In a chat with your Bot, say "Add this MCP server: https://mcp.honeycomb.io/mcp". It confirms the details with you and sets it up, and the tools are ready from your next message.

### Gemini

In Gemini: At gemini.google.com: Settings → Connected Apps → Add a custom app, then paste https://mcp.honeycomb.io/mcp

### Grok

In Grok on the web: At grok.com/connectors: New Connector → Custom, then enter https://mcp.honeycomb.io/mcp and sign in if it asks.

### GitHub Copilot

Add to VS Code: vscode:mcp/install?%7B%22name%22%3A%22honeycomb-mcp%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.honeycomb.io%2Fmcp%22%7D

Copilot CLI:

```shell
copilot mcp add --transport http honeycomb-mcp https://mcp.honeycomb.io/mcp
```

### Cursor

Add to Cursor: cursor://anysphere.cursor-deeplink/mcp/install?name=honeycomb-mcp&config=eyJ1cmwiOiJodHRwczovL21jcC5ob25leWNvbWIuaW8vbWNwIn0%3D

Add to .cursor/mcp.json:

```json
{
  "mcpServers": {
    "honeycomb-mcp": {
      "url": "https://mcp.honeycomb.io/mcp"
    }
  }
}
```

### Claude Code

Run in your terminal:

```shell
claude mcp add --transport http honeycomb-mcp https://mcp.honeycomb.io/mcp
```

### Codex

Run in your terminal:

```shell
codex mcp add honeycomb-mcp --url https://mcp.honeycomb.io/mcp
```

### Antigravity

Add to ~/.gemini/config/mcp_config.json:

```json
{
  "mcpServers": {
    "honeycomb-mcp": {
      "url": "https://mcp.honeycomb.io/mcp"
    }
  }
}
```

### Gemini CLI

Run in your terminal:

```shell
gemini mcp add --transport http honeycomb-mcp https://mcp.honeycomb.io/mcp
```

### Replit

In Replit: At replit.com/integrations, open MCP Servers → + Add MCP server, paste https://mcp.honeycomb.io/mcp (add any headers under Advanced settings), then click Test & save.

### OpenClaw

Run in your terminal:

```shell
openclaw mcp add honeycomb-mcp --url https://mcp.honeycomb.io/mcp --transport streamable-http
```

If it needs a key or sign-in: For https://mcp.honeycomb.io/mcp, add --header NAME=value for each header it needs, or --auth oauth and then run openclaw mcp login honeycomb-mcp.

### OpenCode

Run in your terminal:

```shell
opencode mcp add honeycomb-mcp --url https://mcp.honeycomb.io/mcp
```

If it needs a key: For https://mcp.honeycomb.io/mcp, add --header 'NAME=value' for each header it needs. Add --global to use it in every project.

### Hermes Agent

Run in your terminal:

```shell
hermes mcp add honeycomb-mcp --url https://mcp.honeycomb.io/mcp
```

Add to ~/.hermes/config.yaml:

```json
{
  "mcp_servers": {
    "honeycomb-mcp": {
      "url": "https://mcp.honeycomb.io/mcp"
    }
  }
}
```

If it signs in with OAuth: If https://mcp.honeycomb.io/mcp asks you to sign in, add --auth oauth to the command, or auth: oauth to its entry.

---
From Pluginboard (https://pluginboard.ai).