Send Data with AI Agent

Connect any AI agent that supports the Model Context Protocol (MCP) to Honeycomb, then let it instrument your app, generate sample data, or pick up a pipeline you are already sending. This guide walks through how the process works, then gives exact steps for your client.

Just need to connect your agent to Honeycomb for querying, not sending data? Visit Connect to Honeycomb MCP instead.

How it works

Most AI agents follow the same pattern to start sending data to Honeycomb:

Connect to Honeycomb MCP: Some agents connect with a single prompt or one-click link; others need a short setup step first, depending on whether the client supports the Honeycomb plugin or agent skills.
Run guided onboarding: Once connected, your agent runs Honeycomb’s onboarding prompt (/honeycomb-onboarding), which walks through sending sample data, instrumenting your app for real telemetry, or picking up a pipeline you are already running.
Let your agent do the rest: If you choose real instrumentation, your agent adds OpenTelemetry instrumentation, verifies events are arriving, and can hand off to Canvas for deeper analysis.

Auto-instrumentation depends on the Honeycomb plugin or agent skills being installed. Clients that connect through MCP only still complete onboarding, but guide you through instrumentation manually rather than doing it for you.

Before you begin

Make sure that:

Your Honeycomb team has enabled Honeycomb Intelligence.
Your AI agent supports remote MCP servers or plugins.

Send data by client

For exact setup steps and prompts, select your client:

Send data with Amazon Q Developer using the qchat CLI:

Install the Honeycomb MCP

Select your region and run the associated command in your terminal:

qchat mcp add --name honeycomb --command npx --args mcp-remote,https://mcp.honeycomb.io/mcp

qchat mcp add --name honeycomb --command npx --args mcp-remote,https://mcp.eu1.honeycomb.io/mcp

Onboard with Honeycomb

Run this prompt to start onboarding:

Begin Honeycomb onboarding

Honeycomb opens a browser window to authenticate the first time your agent uses an MCP tool. Grant the requested permissions to finish connecting.Your agent starts guided onboarding against your live Honeycomb account, using sample data, real instrumentation, or data you are already sending. Amazon Q connects through MCP only, so your agent guides you through manual OpenTelemetry instrumentation rather than auto-instrumentation, which is available on AI tools that support the Honeycomb plugin.

Send data with Augment (Auggie CLI) by installing the Honeycomb plugin:

Add the Honeycomb agent skills as a plugin source

Run this in your terminal:

auggie plugin marketplace add honeycombio/agent-skill

To check out the Honeycomb agent skills, visit the agent skills repo.

Install the Honeycomb plugin

Run this in your terminal:

auggie plugin install honeycomb

Set up the Honeycomb MCP

Run this prompt in Auggie and authenticate with Honeycomb when asked:

Set up Honeycomb

Your agent connects to Honeycomb MCP: sets your region, authenticates, and verifies access.

Onboard with Honeycomb

Run this prompt to start onboarding:

Begin Honeycomb onboarding

Your agent starts guided onboarding against your live Honeycomb account. Choose to explore with sample data, instrument your app for real telemetry, or dig into data you are already sending. If you choose real instrumentation, your agent adds OpenTelemetry instrumentation, verifies events are arriving, and hands off to Canvas for deeper analysis.

Send data with Claude Code by installing the Honeycomb plugin:

Install Honeycomb as a Claude Code plugin

Run this in your terminal:

claude plugin marketplace add honeycombio/agent-skill
claude plugin install honeycomb

Set up the Honeycomb MCP

Run this prompt in Claude Code and authenticate with Honeycomb when asked:

Set up Honeycomb

Your agent connects to Honeycomb MCP: sets your region, authenticates, and verifies access.

Onboard with Honeycomb

Once your agent authenticates, use this prompt to discover Honeycomb onboarding:

Begin Honeycomb onboarding

When run, your agent starts guided onboarding against your live Honeycomb account. Choose to explore with sample data, instrument your app for real telemetry, or dig into data you are already sending. If you choose real instrumentation, your agent adds OpenTelemetry instrumentation, verifies events are arriving, and hands off to Canvas for deeper analysis.

Set up Claude Code manually

Add the Honeycomb MCP

Run the command associated with your region in your terminal:

claude mcp add honeycomb --transport http https://mcp.honeycomb.io/mcp

claude mcp add honeycomb --transport http https://mcp.eu1.honeycomb.io/mcp

Add the Honeycomb skills

Download the skills folder from the Honeycomb agent-skill repo and copy it into your skills directory:

  git clone https://github.com/honeycombio/agent-skill.git /tmp/agent-skill-temp
  cp -r /tmp/agent-skill-temp/honeycomb/skills/* ~/.claude/skills/
  rm -rf /tmp/agent-skill-temp

For details on skill locations and scope, see Claude Code’s Agent Skills documentation.

Set up the MCP

Run this prompt in Claude Code and authenticate with Honeycomb when asked:

Set up Honeycomb

Your agent connects to Honeycomb MCP: sets your region, authenticates, and verifies access.

Onboard with Honeycomb

Once your agent authenticates, use this prompt to discover Honeycomb onboarding:

Begin Honeycomb onboarding

Send data with Claude Desktop using the Honeycomb connector and plugin:

Add the Honeycomb connector

Select Customize > Connectors.
Select Add > Browse Connectors.
Search for Honeycomb to go to the Honeycomb connector page.
Select the + on the Honeycomb connector to add it.
When prompted, sign in to Honeycomb and authorize the application. If no browser window opens to prompt authentication over OAuth, fully quit and reopen Claude Desktop.

Install the Honeycomb plugin

Select Customize > Plugins.
Select Browse.
Select the Partners view and search for Honeycomb.
Select the + on the Honeycomb plugin to add it.

Your Honeycomb skills are installed.

Onboard with Honeycomb

Run this prompt to start onboarding:

Begin Honeycomb onboarding

Your agent starts guided onboarding against your live Honeycomb account, using sample data, real instrumentation, or data you are already sending. If you choose real instrumentation, your agent adds OpenTelemetry instrumentation, verifies events are arriving, and hands off to Canvas for deeper analysis.

Send data with OpenAI Codex by installing Honeycomb as a plugin:

Install the Honeycomb plugin

Run this in your terminal:

codex plugin marketplace add honeycombio/agent-skill
codex plugin add honeycomb@honeycomb-plugins

Load the plugin

Restart Codex to load the plugin. This also configures the Honeycomb MCP server for you.

Instrument your application

Ask your AI agent to instrument your application:

Instrument my application

Your agent agent adds OpenTelemetry instrumentation and verifies events are arriving.

Send data with GitHub Copilot by installing the Honeycomb plugin:

Install Honeycomb as a Copilot plugin

Run this in your terminal:

copilot plugin install honeycombio/agent-skill:honeycomb

Set up the Honeycomb MCP

Run this prompt in Copilot and authenticate with Honeycomb when asked:

Set up Honeycomb

Your agent connects to Honeycomb MCP: sets your region, authenticates, and verifies access.

Onboard with Honeycomb

Run this prompt to start onboarding:

Begin Honeycomb onboarding

Send data with Cursor by installing the Honeycomb plugin:

Install Honeycomb as a Cursor plugin

Go to Preferences > Cursor Settings > Customize.
Select the Plugins view.
Select + Add > From Marketplace.
Select + Add Marketplace > Import from Github.
In the Repository field, paste: https://github.com/honeycombio/agent-skill.
Select Import.
Select Manage.
Type honeycomb in the search bar.
Locate the Honeycomb plugin, and select Add to Cursor.

Your MCP server is added and configured.

Authenticate with the Honeycomb MCP

Go to Preferences > Cursor Settings > Customize.
Select the MCPs view.
Locate the Honeycomb MCP, and select Authenticate.

Onboard with Honeycomb

Run this prompt to start onboarding:

Begin Honeycomb onboarding

Next steps

Example Use Cases: Explore real-world use cases and tips for working with Honeycomb via MCP.
Tools Reference: Learn about the tools Honeycomb MCP exposes to AI agents.
Troubleshooting: Fix common MCP configuration and connection issues.

Send Data with AI

Instrument Applications

Instrument Infrastructure

CI/CD Observability

Manage Pipelines

Shape Data

Control Data Volume

Use Cases

How it works

Before you begin

Send data by client

Next steps

​How it works

​Before you begin

​Send data by client

​Next steps

How it works

Before you begin

Send data by client

Next steps