Honeycomb MCP
for LuumenAI
Query Honeycomb datasets for context, then create triggers and boards with approval.
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.
The Honeycomb MCP toolbox
33 tools: 23 read, 10 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadCanvas agent poll responsePoll for the result of a previously-issued canvas_agent_invoke call.
- ReadFind columnsSearch for columns and calculated fields by intent across one or all datasets in an environment.
- ReadFind queriesSearch query history and saved queries by intent; returns matching queries with their run PKs.
- ReadGet aiconversationFetch the full event timeline for a single AI conversation, identified by its OpenTelemetry gen_ai.conversation.id attribute value.
- ReadGet datasetGet dataset metadata and its full column schema (columns + calculated fields), sorted by most recent write activity.
- ReadGet dataset columnsGet the full column schema for one dataset, with optional sample values for specific columns.
- ReadGet environmentGet details for a specific environment, including its dataset list sorted by most recent activity.
- ReadGet query resultsRetrieve results and metadata from an existing query execution.
- ReadGet signalsReturns Anomaly Signals for the current team.
- ReadGet span detailsSummarize attributes and their common values observed on spans with a specific name.
- ReadGet traceRetrieve all spans for a specific trace ID and render them as a waterfall.
- ReadGet triggersList triggers (alert rules) for the team, or fetch full configuration for a single trigger.
- ReadGet workspace contextCall this tool first to orient yourself in a Honeycomb workspace.
- ReadList aiconversationsDiscover recent AI agent conversations (gen_ai.conversation.id values) in an environment, ordered by total event count (most active first) with per-agent activity.
- ReadList boardsList boards (saved dashboards) in an environment, or fetch one board's full contents by ID.
- ReadList recipientsList all pre-registered notification recipients (email, Slack, PagerDuty, webhook) for the team.
- ReadList spansList span names in trace data, ranked by count, with how often each is a trace root and which dataset the count came from.
- ReadMigration guideVendor-specific guidance for migrating existing telemetry to Honeycomb without disrupting the vendor setup.
- ReadRecord onboarding stateRecord the current onboarding step.
- ReadRefinery docsRead Honeycomb Refinery documentation.
- ReadRun bubbleupRun BubbleUp analysis to find what makes a selected data subset different from the baseline.
- ReadRun queryRun an aggregate query or return a scoped set of raw rows from a Honeycomb dataset.
- ReadSemconvQuery the semantic convention registry: the latest embedded OTel semconv release merged with Honeycomb's overlay, plus the team's custom schema when one exists.
- WriteCanvas agent invokeKick off a single-turn run of the Honeycomb Canvas agent. Approval by default
- WriteCreate boardCreate a board (dashboard) with query, SLO, and text panels. Approval by default
- WriteCreate markerCreates a marker (a vertical annotation on charts) to mark a point or window in time, such as a deploy, incident, or config change. Approval by default
- WriteCreate recipientCreate a notification recipient (email, Slack, PagerDuty, or webhook) so it can be attached to triggers and SLO burn alerts. Approval by default
- WriteCreate sloCreate an SLO (Service Level Objective) backed by an auto-created SLI derived column. Approval by default
- WriteCreate triggerCreate a trigger that fires alerts when a query result crosses a threshold. Approval by default
- WriteFeedbackSubmit feedback about Honeycomb's MCP server to the agentic-intelligence team. Approval by default
- WriteUpdate boardEdit an existing board (dashboard) in place. Approval by default
- WriteUpdate sloUpdate an existing SLO. Approval by default
- WriteUpdate triggerUpdate an existing trigger. Approval by default
One prompt, start to finish
What a governed Honeycomb MCP run looks like inside Luumen.
Questions
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.
Read actions answer immediately. Anything that writes — canvas agent invoke, create board, create marker, create recipient, and more — is shown as a plan and requires approval by default, including the 3 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Honeycomb MCP — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Often connected alongside
All integrations
GitHubRepos, actions, and runbook code as context and as actions.
GitLabMerge requests and pipelines proposed, triggered, and rolled back.
BitbucketRead commits, diffs, and branches in Bitbucket, then open the fix as a held write.
Azure DevOpsAzure DevOps repos and pipelines as context — and as approved actions.Put Honeycomb MCP to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.