Skip to main content
hc
Submit
mcpSource-backedReview first Safety ✓ Privacy ✓

Honeycomb MCP Server for Claude

Connect Claude to Honeycomb observability data — query traces and events, investigate alerts, manage boards and triggers, create SLOs, and cross-reference production behavior with your codebase — with the official Honeycomb hosted MCP server.

by Honeycomb·added 2026-06-18·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • The server is hosted by Honeycomb (AWS-backed) and authenticated via OAuth 2.1 or API key — write-scoped access can create/update Boards, Triggers, and SLOs.
  • Writing to Honeycomb resources (boards, triggers, SLOs) requires the `create` scope; verify you grant only the scopes your workflow needs.
  • Canvas investigations and alert management are write operations — review Claude's proposed changes before executing in production environments.

Privacy notes

  • Trace data, event fields, alert details, and query results from Honeycomb are sent through Honeycomb's hosted MCP endpoint and surfaced in Claude's context.
  • Honeycomb API keys (`KEY_ID:SECRET_KEY` format) are secrets — store them in your MCP client config or environment, never in repositories.

Prerequisites

  • A Honeycomb account — any plan including the free tier.
  • For OAuth: authenticate via browser on first tool use.
  • For API key: use format `HONEYCOMB_API_KEY=<KEY_ID>:<SECRET_KEY>` in your MCP client config.
  • EU customers should use `https://mcp.eu1.honeycomb.io/mcp` instead of the US endpoint.
  • An MCP client such as Claude Code or Claude Desktop.

Schema details

Install type
cli
Troubleshooting
No
Collection metadata
Estimated setup
5 minutes
Difficulty
beginner
Tool listing metadata
Full copyable content
{
  "mcpServers": {
    "honeycomb": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.honeycomb.io/mcp"]
    }
  }
}

About this resource

Overview

The Honeycomb MCP Server is the official hosted Model Context Protocol server from Honeycomb. It gives Claude direct access to your Honeycomb observability data — querying traces and events, investigating alerts, managing boards, creating triggers and SLOs, and performing Canvas investigations — through natural language, without leaving your IDE or AI assistant.

The hosted MCP (generally available as of 2026) runs on AWS and is included in all Honeycomb plans at no additional charge. Authentication is via OAuth (recommended) or API key (for headless/automated use). Regional endpoints are available for US and EU.

Key capabilities

  • Trace and event queries — query Honeycomb datasets for spans and events matching your investigation criteria.
  • Alert management — view and investigate open triggers and alerts.
  • Boards — create and update Honeycomb boards for team visibility.
  • Triggers — create and manage alert triggers.
  • SLOs — create and manage Service Level Objectives.
  • Canvas investigations — run structured observability investigations.
  • Cross-referencing — correlate production behavior with codebase changes.

How it compares

Server Trace queries Alert management SLOs Boards Auth
Honeycomb MCP Yes Yes Yes Yes OAuth / API key
New Relic MCP Yes (NRQL) Yes Limited Yes OAuth / API key
Datadog MCP Yes Yes Yes Yes API key
Grafana MCP Limited Yes Yes Limited API key

Honeycomb's MCP is distinct in its focus on high-cardinality trace analysis and structured Canvas investigations, reflecting Honeycomb's event-first observability model.

Installation

Claude Code (OAuth — recommended)

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

Run /mcp in Claude Code to complete the OAuth flow and select your team and scopes.

Claude Code (API key)

claude mcp add honeycomb --transport http \
  --header "Authorization: Bearer KEY_ID:SECRET_KEY" \
  https://mcp.honeycomb.io/mcp

Claude Desktop (OAuth)

{
  "mcpServers": {
    "honeycomb": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.honeycomb.io/mcp"]
    }
  }
}

Restart Claude Desktop; you will be prompted to authenticate via OAuth on first use.

EU region

Replace https://mcp.honeycomb.io/mcp with https://mcp.eu1.honeycomb.io/mcp in all commands.

Requirements

  • A Honeycomb account (any plan, including free tier).
  • An MCP client (Claude Code or Claude Desktop).

Security

  • OAuth is preferred — users grant specific scopes (read vs. read+write) during the OAuth flow.
  • API keys grant the permissions assigned to that key — scope them to the minimum required.
  • KEY_ID:SECRET_KEY API key pairs are secrets — never commit them.

Source Verification Notes

Verified on 2026-06-18:

  • Honeycomb's MCP configuration guide at docs.honeycomb.io/integrations/mcp/configuration-guide documents the US (mcp.honeycomb.io/mcp) and EU (mcp.eu1.honeycomb.io/mcp) endpoints, OAuth 2.1 and API key authentication, the write-scope capabilities (Boards, Triggers, SLOs, Canvas investigations), and the Claude Code and Claude Desktop installation commands.
  • Honeycomb's blog post confirms the hosted MCP is generally available on all plans at no charge, hosted on AWS, and integrated with Cursor, VS Code, and Claude Desktop.
  • Claude Code's MCP documentation describes the --transport http installation pattern used above.
#honeycomb#observability#tracing#monitoring#alerting#slos

Source citations

Add this badge to your README

Show that Honeycomb MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/honeycomb-mcp-server.svg)](https://heyclau.de/entry/mcp/honeycomb-mcp-server)

How it compares

Honeycomb MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

FieldHoneycomb MCP Server for Claude

Connect Claude to Honeycomb observability data — query traces and events, investigate alerts, manage boards and triggers, create SLOs, and cross-reference production behavior with your codebase — with the official Honeycomb hosted MCP server.

Open dossier 		OpenTelemetry MCP Server for Claude

Analyze distributed traces and LLM observability data from Claude — search traces and spans, find errors, list services, analyze LLM token usage, identify slow LLM operations, and discover AI model usage patterns — with the OpenTelemetry MCP server supporting Jaeger, Grafana Tempo, and Traceloop backends.

Open dossier 		Pydantic Logfire MCP Server for Claude

Query OpenTelemetry traces and metrics, manage dashboards, analyze distributed traces, and investigate exceptions from Claude — with the official Pydantic Logfire remote MCP server hosted at logfire-us.pydantic.dev/mcp.

Open dossier 		Arize Phoenix MCP Server for Claude

Inspect LLM traces and spans, manage prompts, explore datasets, and review evaluation experiments from Claude — with the official Arize Phoenix MCP server, built into the open-source Phoenix AI observability platform.

Open dossier
Trust
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Categorymcpmcpmcpmcp
Sourcesource-backedsource-backedsource-backedsource-backed
AuthorHoneycombTraceloopPydanticArize AI
Added2026-06-182026-06-182026-06-182026-06-18
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓The server is hosted by Honeycomb (AWS-backed) and authenticated via OAuth 2.1 or API key — write-scoped access can create/update Boards, Triggers, and SLOs. Writing to Honeycomb resources (boards, triggers, SLOs) requires the `create` scope; verify you grant only the scopes your workflow needs. Canvas investigations and alert management are write operations — review Claude's proposed changes before executing in production environments.✓All tools are read-only — the server queries trace data but does not modify your application or tracing backend. Trace data may contain sensitive information (request parameters, user IDs, SQL queries) — ensure Claude has appropriate access to this data.✓Telemetry data returned by the MCP server may include user-controlled content from traces, logs, exceptions, model payloads, tool arguments, and tool results — treat query results as diagnostic data, not instructions. Dashboard create, update, and delete operations permanently modify your Logfire workspace; review before confirming.✓The `write` and upsert tools can create or modify prompts and add dataset examples — review Claude's proposed changes before confirming. For self-hosted deployments, ensure your Phoenix instance is accessible from the machine running the MCP server.
Privacy notes✓Trace data, event fields, alert details, and query results from Honeycomb are sent through Honeycomb's hosted MCP endpoint and surfaced in Claude's context. Honeycomb API keys (`KEY_ID:SECRET_KEY` format) are secrets — store them in your MCP client config or environment, never in repositories.✓Distributed trace content including service names, operation names, error messages, HTTP parameters, and LLM prompt/response metadata may be surfaced in Claude's context. For Traceloop backend, `BACKEND_API_KEY` is required and grants access to your Traceloop organization's trace data.✓OpenTelemetry trace data, span metadata, exception stack traces, query results, dashboard configurations, and project metadata from your Logfire account are surfaced in Claude's context. Remote MCP uses OAuth — no API keys in your MCP config when authenticating via browser. For API key auth, store the key in MCP config rather than shell history.✓LLM traces (including prompts and completions), evaluation annotations, session data, datasets, and experiment results from your Phoenix workspace are surfaced in Claude's context. Your `PHOENIX_API_KEY` is passed as an environment variable — store it in a secrets manager rather than plaintext shell config.
Prerequisites
  • A Honeycomb account — any plan including the free tier.
  • For OAuth: authenticate via browser on first tool use.
  • For API key: use format `HONEYCOMB_API_KEY=<KEY_ID>:<SECRET_KEY>` in your MCP client config.
  • EU customers should use `https://mcp.eu1.honeycomb.io/mcp` instead of the US endpoint.
  • An OpenTelemetry-compatible tracing backend: Jaeger (local), Grafana Tempo, or Traceloop Cloud.
  • Services instrumented with OpenTelemetry sending traces to your backend.
  • Python 3.11+ with `uvx` available.
  • An MCP client such as Claude Code or Claude Desktop.
  • A Pydantic Logfire account — authenticate via browser OAuth on first use (no API key required).
  • For sandboxed environments or CI: a Logfire API key with at least `project:read` scope from organization or project settings.
  • EU region users: use `https://logfire-eu.pydantic.dev/mcp` instead of the US endpoint.
  • An MCP client such as Claude Code or Claude Desktop.
  • An Arize Phoenix account (cloud at app.phoenix.arize.com) or self-hosted Phoenix instance.
  • A Phoenix API key from your account settings.
  • Node.js 18+ for `npx`.
  • An MCP client such as Claude Code or Claude Desktop.
Install
claude mcp add honeycomb --transport http https://mcp.honeycomb.io/mcp
claude mcp add opentelemetry -e BACKEND_TYPE=jaeger -e BACKEND_URL=http://localhost:16686 -- uvx opentelemetry-mcp
claude mcp add logfire --transport http https://logfire-us.pydantic.dev/mcp
claude mcp add phoenix -e PHOENIX_HOST=https://app.phoenix.arize.com -e PHOENIX_API_KEY=your-key -- npx -y @arizeai/phoenix-mcp@latest
Config
{
  "mcpServers": {
    "honeycomb": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.honeycomb.io/mcp"]
    }
  }
}
{
  "mcpServers": {
    "opentelemetry": {
      "command": "uvx",
      "args": ["opentelemetry-mcp"],
      "env": {
        "BACKEND_TYPE": "jaeger",
        "BACKEND_URL": "http://localhost:16686",
        "MAX_TRACES_PER_QUERY": "100",
        "BACKEND_TIMEOUT": "30"
      }
    }
  }
}
{
  "mcpServers": {
    "logfire": {
      "type": "http",
      "url": "https://logfire-us.pydantic.dev/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_LOGFIRE_API_KEY"
      }
    }
  }
}
{
  "mcpServers": {
    "phoenix": {
      "command": "npx",
      "args": ["-y", "@arizeai/phoenix-mcp@latest"],
      "env": {
        "PHOENIX_HOST": "https://app.phoenix.arize.com",
        "PHOENIX_API_KEY": "your-api-key"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.