---
title: "Kiwi for Honeycomb"
description: "Have the agent on a Kiwi step query Honeycomb traces and run BubbleUp on slow requests, through Honeycomb's MCP server."
canonical: "https://kiwiflow.io/integrations/honeycomb"
---

# Kiwi for Honeycomb

Have the agent on a Kiwi step query Honeycomb traces and run BubbleUp on slow requests, through Honeycomb's MCP server.

- Your agent works in Honeycomb through its own connection. Kiwi does not call Honeycomb and never holds its credentials.
- A workflow skill can list Honeycomb among the tools it requires. When you supply your agent's available tools to a skill check and Honeycomb is not among them, the check reports `SK15-UNSUPPORTED-TOOL`.
- A project Admin can add links to Honeycomb, with notes, under Connections and bind them to the steps that use them. The agent reads them with `list_connections`.
- The agent can report the tools and plugins it ran with, including its Honeycomb connection, with `report_configuration`.
- The agent submits links to its work in Honeycomb as the step's outputs. People review them, and sign-off stays with the people your workflow names.

## What your agent can do in Honeycomb

- Run a query against a dataset and find the columns to group or filter by.
- Run BubbleUp to see which attributes set outlier events apart from the rest.
- Fetch a trace and read the details of its spans.
- Read the service map, boards, triggers and SLOs of an environment.

## Set up

### 1. Connect your agent to Kiwi

Add Kiwi's hosted MCP server, `https://kiwiflow.io/mcp`, to your coding agent.

- [Coding agents](https://kiwiflow.io/integrations#agent)
- [Quickstart](https://docs.kiwiflow.io/quickstart#connect-your-agent)

### 2. Connect your agent to Honeycomb

Add the Honeycomb MCP server to your agent with this URL. The credentials stay with your agent.

```
https://mcp.honeycomb.io/mcp
```

- [Honeycomb documentation](https://docs.honeycomb.io/integrations/mcp/configuration-guide)

### 3. Example skill

Publish instructions like these as a workflow skill that lists Honeycomb among its required tools.

```
Start from the endpoint and the latency target given in the run's inputs.
In Honeycomb, query that endpoint's spans for the last 24 hours and run
BubbleUp on the requests slower than the target.
Submit the queries you ran and the attributes BubbleUp found as outputs.
If the dataset has no spans for the endpoint, report a blocker to the Owner.
```

## More monitoring and incidents integrations

- [Kiwi for Sentry](https://kiwiflow.io/integrations/sentry.md): Have the agent on a Kiwi step read the Sentry issue behind a bug, with its stack trace and events, before it fixes the code, through Sentry's MCP server.
- [Kiwi for Datadog](https://kiwiflow.io/integrations/datadog.md): Have the agent on a Kiwi step check Datadog logs, traces and monitors for the service it changed, through Datadog's remote MCP server.
- [Kiwi for Grafana](https://kiwiflow.io/integrations/grafana.md): Have the agent on a Kiwi step query Prometheus and Loki through Grafana and link the dashboard panel it checked, using the Grafana MCP server.
- [Kiwi for New Relic](https://kiwiflow.io/integrations/new-relic.md): Have the agent on a Kiwi step run NRQL queries and check how a release changed an application in New Relic, through New Relic's MCP server.
- [Kiwi for PagerDuty](https://kiwiflow.io/integrations/pagerduty.md): Have the agent on a Kiwi step read a PagerDuty incident, add its findings as a note and find who is on call, through PagerDuty's MCP server.
- [Kiwi for Dynatrace](https://kiwiflow.io/integrations/dynatrace.md): Have the agent on a Kiwi step investigate a Dynatrace problem with DQL queries and cite what it found, through the Dynatrace MCP server.
- [Kiwi for incident.io](https://kiwiflow.io/integrations/incident-io.md): Have the agent on a Kiwi step read an incident.io incident, post updates to it and create follow-ups, through incident.io's remote MCP server.

- [Get started](https://kiwiflow.io/get-started)
- [Read the setup guide](https://docs.kiwiflow.io/other-tools)