Honeycomb

listing.by

Query Honeycomb traces, events, metrics, SLOs, triggers and boards to investigate production issues from your AI assistant.

state.auth.long (state.auth.title)Streamable HTTP

listing.connect

listing.explain.oauth

https://mcp.honeycomb.io/mcp

listing.note.oauth

listing.share.h

listing.share.p

mcp.tc/i/honeycomb

listing.about

Connects an AI assistant to Honeycomb observability data. Agents can run queries against telemetry, explore traces, and work with SLOs, triggers and boards. Honeycomb's docs describe uses such as investigating latency or error spikes, finding performance outliers, and translating existing dashboards and alerts into Honeycomb queries.

Runs as a hosted streamable HTTP endpoint at https://mcp.honeycomb.io/mcp. Users sign in with OAuth through Honeycomb, with mcp:read and mcp:write scopes. No local install is needed.

listing.can

  • Query traces, events and metrics in Honeycomb
  • Investigate latency and error spikes
  • Find performance outliers
  • Work with SLOs and triggers
  • Create and read boards to capture findings
  • Translate existing dashboards and alerts into Honeycomb queries

listing.tools

listing.notools.oauth

listing.prompts

  • Why did p99 latency spike on the checkout service in the last hour?

  • Show the slowest traces for the payments service today

  • Which SLOs are burning budget fastest right now?

  • Create a board with the queries we used to investigate this error spike

listing.setup.h

listing.setup.oauth

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http honeycomb https://mcp.honeycomb.io/mcp
  1. Start Claude Code, type /mcp, pick honeycomb and choose Authenticate. A browser window opens for the Honeycomb sign-in.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Settings → Connectors and click Add custom connector.
  2. Name it Honeycomb and paste this URL:
https://mcp.honeycomb.io/mcp
  1. Click Add, then Connect, and sign in when Honeycomb asks.

Claude Desktop's JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://mcp.honeycomb.io/mcp and click Add.
  2. Click Connect and sign in when Honeycomb asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, open Settings → Security and login and turn on Developer mode.
  2. Go to chatgpt.com/plugins and click + to create an app for a remote MCP server.
  3. Paste https://mcp.honeycomb.io/mcp as the server URL and choose OAuth. ChatGPT sends you to Honeycomb to sign in.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

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

Cursor shows Needs login next to the server. Click it to sign in.

VS Code

Or from a terminal:

code --add-mcp '{"name":"honeycomb","type":"http","url":"https://mcp.honeycomb.io/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "honeycomb": {
      "type": "http",
      "url": "https://mcp.honeycomb.io/mcp"
    }
  }
}

VS Code asks you to sign in the first time the server starts.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "honeycomb": {
      "serverUrl": "https://mcp.honeycomb.io/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add honeycomb --url https://mcp.honeycomb.io/mcp
codex mcp login honeycomb

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.honeycomb]
url = "https://mcp.honeycomb.io/mcp"

Gemini CLI

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

Then, inside Gemini CLI, run /mcp auth honeycomb to sign in.

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI's settings file.

{
  "mcpServers": {
    "honeycomb": {
      "type": "http",
      "url": "https://mcp.honeycomb.io/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://mcp.honeycomb.io/mcp.

listing.faq

Can I paste mcp.tc/i/honeycomb into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://mcp.honeycomb.io/mcp, so your client talks to Honeycomb directly. The sign-in token only works there anyway. The quick link is for sharing: it opens this page, with setup steps for every client.

Does Honeycomb need an API key or a sign-in?

Yes, you need a Honeycomb account. The first time your client connects, it opens Honeycomb's sign-in page. The token goes straight to the server's own URL, never through mcp.tc.

Is Honeycomb a remote or a local server?

Remote. Honeycomb hosts it at https://mcp.honeycomb.io/mcp, and it speaks Streamable HTTP. There's nothing to install.

What can Honeycomb do?

You can query traces, events and metrics in Honeycomb, investigate latency and error spikes and find performance outliers.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT in developer mode, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Who wrote this page?

mcp.tc's robot read Honeycomb's own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can't confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

listing.em.h

listing.em.lead listing.em.how

listing.em.badge

em.prev_lightem.prev_dark
Markdown
[![Honeycomb on mcp.tc](https://mcp.tc/i/honeycomb/badge.svg)](https://mcp.tc/i/honeycomb)
HTML
<a href="https://mcp.tc/i/honeycomb"><img src="https://mcp.tc/i/honeycomb/badge.svg" alt="Honeycomb on mcp.tc" height="20"></a>

listing.em.badge_note

listing.em.widget

HTML
<script src="https://mcp.tc/w/honeycomb.js" async></script>

listing.em.widget_note

iframe

HTML
<iframe src="https://mcp.tc/embed/honeycomb" title="Honeycomb on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

listing.em.iframe_note

JSON

listing.em.json

https://mcp.tc/i/honeycomb.json

listing.em.fields

listing.disclaimer_checked