Skip to main content

Honeycomb

Query Honeycomb traces and keep SLOs and triggers in shape.

Tools

38 available tools

Search the tool definitions captured from the MCP server. The live list can vary with version, deployment, and credentials.

38 tools found.

  • Canvas agent invoke

    Tool name: canvas_agent_invoke

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

  • Canvas agent poll response

    Tool name: canvas_agent_poll_response

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

  • Create board

    Tool name: create_board

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

  • Create burn alert

    Tool name: create_burn_alert

    Create a burn alert on an SLO.

  • Create marker

    Tool name: 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.

  • Create recipient

    Tool name: create_recipient

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

  • Create slo

    Tool name: create_slo

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

  • Create trigger

    Tool name: create_trigger

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

  • Feedback

    Tool name: feedback

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

  • Find columns

    Tool name: find_columns

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

  • Find queries

    Tool name: find_queries

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

  • Get aiconversation

    Tool name: get_aiconversation

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

  • Get dataset

    Tool name: get_dataset

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

  • Get dataset columns

    Tool name: get_dataset_columns

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

  • Get environment

    Tool name: get_environment

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

  • Get query results

    Tool name: get_query_results

    Retrieve results and metadata from an existing query execution.

  • Get service map

    Tool name: get_service_map

    Get a snapshot of service-to-service call dependencies for a specified time range.

  • Get signals

    Tool name: get_signals

    Returns Anomaly Signals for the current team.

  • Get slos

    Tool name: get_slos

    List SLOs for the team, or fetch detailed status and graphs for a single SLO.

  • Get span details

    Tool name: get_span_details

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

  • Get trace

    Tool name: get_trace

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

  • Get triggers

    Tool name: get_triggers

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

  • Get workspace context

    Tool name: get_workspace_context

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

  • List aiconversations

    Tool name: list_aiconversations

    Discover recent AI agent conversations (gen_ai.conversation.id values) in an environment, ordered by total event count (most active first) with per-agent activity.

  • List boards

    Tool name: list_boards

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

  • List recipients

    Tool name: list_recipients

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

  • List spans

    Tool name: list_spans

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

  • Migration guide

    Tool name: migration_guide

    Vendor-specific guidance for migrating existing telemetry to Honeycomb without disrupting the vendor setup.

  • Record onboarding state

    Tool name: record_onboarding_state

    Record the current onboarding step.

  • Refinery docs

    Tool name: refinery_docs

    Read Honeycomb Refinery documentation.

  • Reset slo budget

    Tool name: reset_slo_budget

    Reset an SLO's error budget.

  • Run bubbleup

    Tool name: run_bubbleup

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

  • Run query

    Tool name: run_query

    Run an aggregate query or return a scoped set of raw rows from a Honeycomb dataset.

  • Semconv

    Tool name: semconv

    Query the semantic convention registry: the latest embedded OTel semconv release merged with Honeycomb's overlay, plus the team's custom schema when one exists.

  • Update board

    Tool name: update_board

    Edit an existing board (dashboard) in place.

  • Update burn alert

    Tool name: update_burn_alert

    Update a burn alert on an SLO.

  • Update slo

    Tool name: update_slo

    Update an existing SLO.

  • Update trigger

    Tool name: update_trigger

    Update an existing trigger.

Compatibility

Connect Honeycomb to the clients your teams already use

27 AI clients can connect to Honeycomb through Runlayer. Pick one for its setup steps and controls.

Why Runlayer

Why connect Honeycomb through Runlayer?

One approved path

Approve Honeycomb once and everyone gets it in the AI clients they already use. Runlayer holds the credentials, so nothing sits in client configuration.

Fine-grained policy

Control who can use each server, tool, and resource, and under which runtime conditions.

Runtime security

Scan tool inputs and outputs for prompt injection, credential exposure, PII, and data exfiltration, then alert, mask, or block.

Audit and observability

Trace every request across users, clients, tools, policies, scanner decisions, and downstream systems.

Frequently asked questions