[ MCP SERVER SUMMARY ]
Honeycomb's hosted MCP server lets AI agents query traces, investigate anomalies with BubbleUp, check Triggers and SLOs, and create Boards — all against your observability data. Bifrost adds governance so only approved teams can run Honeycomb tools, with credentials and audit logs at the gateway.
| Property | Details |
|---|---|
| Company | Honeycomb |
| Connection type | HTTP |
| Authentication | OAuth 2.1 (recommended) or Management API key |
| Package or endpoint | https://mcp.honeycomb.io/mcp |
| Capabilities | Query traces metrics and logs, Triggers and SLO inspection, Boards and investigation workflows |
| Official documentation | Honeycomb MCP documentation |
[ HOW TO CONNECT ]
Start the gateway locally or deploy in your VPC.
npx -y @maximhq/bifrost
Open MCP Gateway in the Bifrost dashboard, click New MCP Server, and choose HTTP. Or register via the API below.
• US: https://mcp.honeycomb.io/mcp — EU: https://mcp.eu1.honeycomb.io/mcp.
• OAuth is recommended. For API-key auth, follow Honeycomb’s Management API key + MCP scopes guide.
Configure Claude Desktop, Cursor, or Claude Code to use your Bifrost endpoint with a virtual key instead of connecting directly to Honeycomb.
{
"mcpServers": {
"bifrost": {
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer vk_your_virtual_key"
}
}
}
}[ EXAMPLE CONFIG ]
Add this MCP client with a POST to /api/mcp/client. See Connecting to MCP Servers for full options.
curl -X POST http://localhost:8080/api/mcp/client \
-H "Content-Type: application/json" \
-d '{
"name": "honeycomb",
"connection_type": "http",
"connection_string": "https://mcp.honeycomb.io/mcp",
"auth_type": "oauth",
"tools_to_execute": [
"*"
]
}'[ WHY BIFROST ]
Virtual keys, RBAC, and tool allowlists per team or agent.
Attribute MCP tool spend alongside LLM usage in one view.
Log every tool call with latency, server, and virtual key metadata.
Upstream secrets stay in the gateway — not on every laptop.
[ FAQ ]
Honeycomb exposes query traces metrics and logs, triggers and slo inspection, boards and investigation workflows to MCP-compatible AI clients. Bifrost connects to it as an upstream MCP client and exposes approved tools through one governed /mcp endpoint.
Honeycomb uses OAuth 2.1 (recommended) or Management API key. Store credentials in Bifrost's environment or credential configuration so they stay at the gateway instead of being copied into every AI client.
Yes. After registering Honeycomb in Bifrost, point any HTTP MCP-compatible client at the Bifrost /mcp endpoint and authenticate with a virtual key. The client sees only the tools allowed for that key.
[ RELATED SERVERS ]
Use Sentry’s MCP server to investigate errors, issues, traces, and application health from AI coding assistants.

GitLab's official MCP server enabling AI tools to securely access GitLab project data, manage issues, and perform repository operations via OAuth 2.0.

GitHub's official MCP Server.