Connect your AI agents to Honeycomb MCP using OAuth or API keys.
You can connect Honeycomb to any AI agent that supports the Model Context Protocol (MCP). This guide shows you how to set up that connection using either OAuth 2.1 (recommended) or API key authentication.
Make sure you have:
Honeycomb supports two authentication methods for MCP:
Many modern agents support OAuth out of the box or through a few CLI commands. Once connected, your agent can access Honeycomb’s MCP tools without needing a key or manual setup.
If your tool supports one-click or command-line configuration, use one of these options:
Cursor: Set up Honeycomb with Cursor
Visual Studio Code: Configure Honeycomb with VS Code
Claude Desktop (Free version): Download the Honeycomb connector
For Claude Enterprise or Pro/Max accounts, set up a custom connector using the appropriate Honeycomb MCP endpoint:
https://mcp.honeycomb.io/mcp
https://mcp.eu1.honeycomb.io/mcp
You can also connect using built-in CLI support:
claude mcp add honeycomb --transport http https://mcp.honeycomb.io/mcp
claude mcp add honeycomb --transport http https://mcp.eu1.honeycomb.io/mcp
qchat mcp add --name honeycomb --command npx --args mcp-remote,https://mcp.honeycomb.io/mcp
qchat mcp add --name honeycomb --command npx --args mcp-remote,https://mcp.eu1.honeycomb.io/mcp
If your agent does not support one-click integration, you can still connect manually:
Find the setting or preference for adding an MCP Server.
Create a new server with these parameters:
https://mcp.honeycomb.io/mcp
https://mcp.eu1.honeycomb.io/mcp
Your agent should guide you through the OAuth flow to authenticate and authorize your Honeycomb account.
If your agent does not support HTTP streaming (or if you encounter issues), you can fall back to a stdio
bridge like mcp-remote
.
Here’s a sample mcp.json
for that option:
{
"mcpServers": {
"honeycomb": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.honeycomb.io/mcp",
],
}
}
}
If you are building autonomous or unattended agents and cannot use OAuth, then you can authenticate with an API key.
The exact configuration process varies by agent, but here is an example configuration mcp.json
snippet used by agents like Claude Code or Cursor:
KEY_ID
and SECRET_KEY
with your actual key values.{
"mcpServers": {
"honeycomb": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.honeycomb.io/mcp",
"--header",
"Authorization: Bearer $HONEYCOMB_API_KEY"
],
"env": {
"HONEYCOMB_API_KEY": "<KEY_ID>:<SECRET_KEY>"
}
}
}
}
Watch out formatting, including spacing and colon (:
) characters.
If your tool cannot parse the Authorization
header correctly, try putting the Bearer
prefix directly in the environment variable:
"HONEYCOMB_API_KEY": "Bearer KEY_ID:SECRET_KEY"
.
As a security best practice, make sure that keys being used for MCP integrations do not carry any other scopes, and that you do not commit them to source control.
Once connected, test by asking your agent t o list available tools or fetch available teams and environments. You should get results if your key and permissions are set up correctly.
Continue your MCP journey with these focused resources: