---
title: "Honeycomb MCP integration for LuumenAI"
url: "https://www.luumen.ai/integrations/honeycomb-mcp/"
entity: SoftwareIntegration
category: "Source control & CI/CD"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Honeycomb MCP integration for LuumenAI

Query Honeycomb datasets for context, then create triggers and boards with approval.

## What LuumenAI can do with Honeycomb MCP

LuumenAI connects to Honeycomb MCP with OAuth 2.0 and exposes 33 tools (23 read-only · 7 write · 3 destructive). For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

## Key facts

- Authentication: OAuth 2.0
- Tools available: 33 tools (23 read-only · 7 write · 3 destructive)
- Deployment: scoped as part of your Pilot, Platform, or Managed rollout
- Category: Source control & CI/CD

## About Honeycomb MCP with LuumenAI

Connect Honeycomb and Luumen can read your telemetry the way you would: pull a dataset's column schema, replay a trace as a waterfall, check existing triggers and anomaly signals. When the investigation points to a change — a new trigger, an SLO, a deploy marker — Luumen writes it back to Honeycomb as a step you approve first. Auth is handled through OAuth.

## Example tools

Read-only (23 in total):

- `HONEYCOMB_MCP_CANVAS_AGENT_POLL_RESPONSE` — Poll for the result of a previously-issued canvas_agent_invoke call.
- `HONEYCOMB_MCP_FIND_COLUMNS` — Search for columns and calculated fields by intent across one or all datasets in an environment.
- `HONEYCOMB_MCP_FIND_QUERIES` — Search query history and saved queries by intent; returns matching queries with their run PKs.
- `HONEYCOMB_MCP_GET_AICONVERSATION` — Fetch the full event timeline for a single AI conversation, identified by its OpenTelemetry gen_ai.conversation.id attribute value.
- `HONEYCOMB_MCP_GET_DATASET` — Get dataset metadata and its full column schema (columns + calculated fields), sorted by most recent write activity.
- `HONEYCOMB_MCP_GET_DATASET_COLUMNS` — Get the full column schema for one dataset, with optional sample values for specific columns.
- `HONEYCOMB_MCP_GET_ENVIRONMENT` — Get details for a specific environment, including its dataset list sorted by most recent activity.
- `HONEYCOMB_MCP_GET_QUERY_RESULTS` — Retrieve results and metadata from an existing query execution.

Write and destructive (10 in total, subject to configured approval policy):

- `HONEYCOMB_MCP_CANVAS_AGENT_INVOKE` — Kick off a single-turn run of the Honeycomb Canvas agent.
- `HONEYCOMB_MCP_CREATE_BOARD` — Create a board (dashboard) with query, SLO, and text panels.
- `HONEYCOMB_MCP_CREATE_MARKER` — Creates a marker (a vertical annotation on charts) to mark a point or window in time, such as a deploy, incident, or config change.
- `HONEYCOMB_MCP_CREATE_RECIPIENT` — Create a notification recipient (email, Slack, PagerDuty, or webhook) so it can be attached to triggers and SLO burn alerts.
- `HONEYCOMB_MCP_CREATE_SLO` — Create an SLO (Service Level Objective) backed by an auto-created SLI derived column.
- `HONEYCOMB_MCP_CREATE_TRIGGER` — Create a trigger that fires alerts when a query result crosses a threshold.
- `HONEYCOMB_MCP_FEEDBACK` — Submit feedback about Honeycomb's MCP server to the agentic-intelligence team.
- `HONEYCOMB_MCP_UPDATE_BOARD` — Edit an existing board (dashboard) in place.

## Frequently asked questions

### How does LuumenAI connect to Honeycomb MCP?

Authorize once with OAuth 2.0. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Honeycomb MCP on its own?

For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

### Is there an audit trail?

Every call to Honeycomb MCP — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/honeycomb-mcp/