How to integrate Honeycomb MCP with Codex

Kick off a single-turn run of the Honeycomb Canvas agent.

Poll for the result of a previously-issued canvas_agent_invoke call.

Create a board (dashboard) with query, SLO, and text panels.

Creates a marker (a vertical annotation on charts) to mark a point or window in time, such as a deploy, incident, or config change.

Create a notification recipient (email, Slack, PagerDuty, or webhook) so it can be attached to triggers and SLO burn alerts.

Create an SLO (Service Level Objective) backed by an auto-created SLI derived column.

Create a trigger that fires alerts when a query result crosses a threshold.

Submit feedback about Honeycomb's MCP server to the agentic-intelligence team.

Search for columns and calculated fields by intent across one or all datasets in an environment.

Search query history and saved queries by intent; returns matching queries with their run PKs.

Fetch the full event timeline for a single AI conversation, identified by its OpenTelemetry gen_ai.

Get dataset metadata and its full column schema (columns + calculated fields), sorted by most recent write activity.

Get the full column schema for one dataset, with optional sample values for specific columns.

Get details for a specific environment, including its dataset list sorted by most recent activity.

Retrieve results and metadata from an existing query execution.

Get the full definitions of one or more semantic convention attributes by their exact names.

Summarize attributes and their common values observed on spans with a specific name.

Retrieve all spans for a specific trace ID and render them as a waterfall.

List triggers (alert rules) for the team, or fetch full configuration for a single trigger.

Call this tool first to orient yourself in a Honeycomb workspace.

Discover recent AI agent conversations (gen_ai.

List boards (saved dashboards) in an environment, or fetch one board's full contents by ID.

List all pre-registered notification recipients (email, Slack, PagerDuty, webhook) for the team.

List the top-level semantic convention namespaces available in this team's registry.

List span names in trace data, ranked by count, with how often each is a trace root and which dataset the count came from.

Read Honeycomb Refinery documentation.

Run BubbleUp analysis to find what makes a selected data subset different from the baseline.

Run a time-series aggregation query against a Honeycomb dataset and return computed results.

Search the semantic convention registry for attributes matching a query.

Edit an existing board (dashboard) in place.

Update an existing SLO.

Update an existing trigger.