> ## Documentation Index
> Fetch the complete documentation index at: https://docs.honeycomb.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Send Data with AI Agent

> Connect your AI agent to Honeycomb MCP and start sending data using sample data, real instrumentation, or a pipeline you are already running.

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.

<Tip>
  Just need to connect your agent to Honeycomb for querying, not sending data?
  Visit [Connect to Honeycomb MCP](/integrations/mcp/configuration-guide) instead.
</Tip>

## How it works

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

1. **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.
2. **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.
3. **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](/investigate/canvas/) for deeper analysis.

<Tip>
  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.
</Tip>

## Before you begin

Make sure that:

* Your Honeycomb team has [enabled Honeycomb Intelligence](/configure/teams/manage-behavior#enable-honeycomb-intelligence).
* Your AI agent supports remote MCP servers or plugins.

## Send data by client

For exact setup steps and prompts, select your client:

<div className="hny-client-tabs">
  <Tabs>
    <Tab title="Amazon Q">
      Send data with Amazon Q Developer using the qchat CLI:

      <Steps>
        <Step title="Install the Honeycomb MCP">
          Select your region and run the associated command in your terminal:

          <Tabs>
            <Tab title="US">
              ```bash wrap theme={}
              qchat mcp add --name honeycomb --command npx --args mcp-remote,https://mcp.honeycomb.io/mcp
              ```
            </Tab>

            <Tab title="EU">
              ```bash wrap theme={}
              qchat mcp add --name honeycomb --command npx --args mcp-remote,https://mcp.eu1.honeycomb.io/mcp
              ```
            </Tab>
          </Tabs>
        </Step>

        <Step title="Onboard with Honeycomb">
          Run this prompt to start onboarding:

          <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
            /honeycomb-onboarding
          </Prompt>

          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](/integrations/agent-skills).
        </Step>
      </Steps>
    </Tab>

    <Tab title="Auggie CLI">
      Send data with Augment (Auggie CLI) by installing the Honeycomb plugin:

      <Steps>
        <Step title="Add the Honeycomb agent skills as a plugin source">
          Run this in your terminal:

          ```bash theme={}
          auggie plugin marketplace add honeycombio/agent-skill
          ```

          <Tip>
            To check out the Honeycomb agent skills, [visit the agent skills repo](https://github.com/honeycombio/agent-skill).
          </Tip>
        </Step>

        <Step title="Install the Honeycomb plugin">
          Run this in your terminal:

          ```bash theme={}
          auggie plugin install honeycomb
          ```
        </Step>

        <Step title="Set up the Honeycomb MCP">
          Run this prompt in Auggie and authenticate with Honeycomb when asked:

          <Prompt description="Set up Honeycomb" icon="sparkle">
            /honeycomb-setup
          </Prompt>

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

        <Step title="Onboard with Honeycomb">
          Run this prompt to start onboarding:

          <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
            /honeycomb-onboarding
          </Prompt>

          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.
        </Step>
      </Steps>
    </Tab>

    <Tab title="ChatGPT">
      Send data with ChatGPT by installing the Honeycomb app from ChatGPT's app directory:

      <Steps>
        <Step title="Install Honeycomb as a ChatGPT plugin">
          1. [Go to the Honeycomb plugin page](https://chatgpt.com/plugins/plugin_asdk_app_6a51b29fa2d48191b215ff28f9a64fb4).
          2. Select **Install plugin**.
          3. When prompted, sign in to Honeycomb to finish authentication.
        </Step>

        <Step title="Onboard with Honeycomb">
          Run this prompt to start onboarding:

          <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
            /honeycomb-onboarding
          </Prompt>

          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.
        </Step>
      </Steps>
    </Tab>

    <Tab title="Claude Code">
      Send data with Claude Code by installing the Honeycomb plugin:

      <Steps>
        <Step title="Install Honeycomb as a Claude Code plugin">
          Run this in your terminal:

          ```bash theme={}
          claude plugin marketplace add honeycombio/agent-skill
          claude plugin install honeycomb
          ```
        </Step>

        <Step title="Set up the Honeycomb MCP">
          Run this prompt in Claude Code and authenticate with Honeycomb when asked:

          <Prompt description="Set up Honeycomb" icon="sparkle">
            /honeycomb-setup
          </Prompt>

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

        <Step title="Onboard with Honeycomb">
          Once your agent authenticates, use this prompt to discover Honeycomb onboarding:

          <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
            /honeycomb-onboarding
          </Prompt>

          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.
        </Step>
      </Steps>

      <Accordion title="Set up Claude Code manually">
        <Steps>
          <Step title="Add the Honeycomb MCP">
            Run the command associated with your region in your terminal:

            <Tabs>
              <Tab title="US">
                ```bash wrap theme={}
                claude mcp add honeycomb --transport http https://mcp.honeycomb.io/mcp
                ```
              </Tab>

              <Tab title="EU">
                ```bash wrap theme={}
                claude mcp add honeycomb --transport http https://mcp.eu1.honeycomb.io/mcp
                ```
              </Tab>
            </Tabs>
          </Step>

          <Step title="Add the Honeycomb skills">
            Download the skills folder from the [Honeycomb agent-skill repo](https://github.com/honeycombio/agent-skill/tree/main/honeycomb/skills) and copy it into your skills directory:

            ```bash theme={}
              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](https://docs.claude.com/en/docs/claude-code/skills).
          </Step>

          <Step title="Set up the MCP">
            Run this prompt in Claude Code and authenticate with Honeycomb when asked:

            <Prompt description="Set up Honeycomb" icon="sparkle">
              /honeycomb-setup
            </Prompt>

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

          <Step title="Onboard with Honeycomb">
            Once your agent authenticates, use this prompt to discover Honeycomb onboarding:

            <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
              /honeycomb-onboarding
            </Prompt>

            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.
          </Step>
        </Steps>
      </Accordion>
    </Tab>

    <Tab title="Claude Desktop">
      Send data with Claude Desktop using the Honeycomb connector and plugin:

      <Steps>
        <Step title="Add the Honeycomb connector">
          1. Select **Customize** > **Connectors**.
          2. Select **Add** > **Browse Connectors**.
          3. Search for `Honeycomb` to go to the [Honeycomb connector](https://claude.ai/directory/connectors/honeycomb) page.
          4. Select the `+` on the Honeycomb connector to add it.
          5. 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.
        </Step>

        <Step title="Install the Honeycomb plugin">
          1. Select **Customize** > **Plugins**.
          2. Select **Browse**.
          3. Select the **Partners** view and search for Honeycomb.
          4. Select the `+` on the Honeycomb plugin to add it.

          Your Honeycomb skills are installed.
        </Step>

        <Step title="Onboard with Honeycomb">
          Run this prompt to start onboarding:

          <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
            /honeycomb-onboarding
          </Prompt>

          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.
        </Step>
      </Steps>
    </Tab>

    <Tab title="Codex">
      Send data with OpenAI Codex by installing Honeycomb as a plugin:

      <Steps>
        <Step title="Install the Honeycomb plugin">
          Run this in your terminal:

          ```bash theme={}
          codex plugin marketplace add honeycombio/agent-skill
          codex plugin add honeycomb@honeycomb-plugins
          ```
        </Step>

        <Step title="Load the plugin">
          Restart Codex to load the plugin.
          This also configures the Honeycomb MCP server for you.
        </Step>

        <Step title="Instrument your application">
          Ask your AI agent to instrument your application:

          <Prompt description="Instrument my application" icon="sparkle">
            Use the otel-instrumentation skill to instrument my application to send traces to Honeycomb using OpenTelemetry.

            Set up auto-instrumentation and add custom spans for the key operations in my codebase.
            Use the query-patterns skill to verify data is flowing correctly.
          </Prompt>

          Your agent agent adds OpenTelemetry instrumentation and verifies events are arriving.
        </Step>
      </Steps>
    </Tab>

    <Tab title="Copilot">
      Send data with GitHub Copilot by installing the Honeycomb plugin:

      <Steps>
        <Step title="Install Honeycomb as a Copilot plugin">
          Run this in your terminal:

          ```bash theme={}
          copilot plugin install honeycombio/agent-skill:honeycomb
          ```
        </Step>

        <Step title="Set up the Honeycomb MCP">
          Run this prompt in Copilot and authenticate with Honeycomb when asked:

          <Prompt description="Set up Honeycomb" icon="sparkle">
            /honeycomb-setup
          </Prompt>

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

        <Step title="Onboard with Honeycomb">
          Run this prompt to start onboarding:

          <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
            /honeycomb-onboarding
          </Prompt>

          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.
        </Step>
      </Steps>
    </Tab>

    <Tab title="Cursor">
      Send data with Cursor by installing the Honeycomb plugin:

      <Steps>
        <Step title="Install Honeycomb as a Cursor plugin">
          1. Go to **Preferences** > **Cursor Settings** > **Customize**.
          2. Select the **Plugins** view.
          3. Select **+ Add** > **From Marketplace**.
          4. Select **+ Add Marketplace** > **Import from Github**.
          5. In the **Repository** field, paste: `https://github.com/honeycombio/agent-skill`.
          6. Select **Import**.
          7. Select **Manage**.
          8. Type `honeycomb` in the search bar.
          9. Locate the Honeycomb plugin, and select **Add to Cursor**.

          Your MCP server is added and configured.
        </Step>

        <Step title="Authenticate with the Honeycomb MCP">
          1. Go to **Preferences** > **Cursor Settings** > **Customize**.
          2. Select the **MCPs** view.
          3. Locate the Honeycomb MCP, and select **Authenticate**.
        </Step>

        <Step title="Onboard with Honeycomb">
          Run this prompt to start onboarding:

          <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
            /honeycomb/honeycomb-onboarding
          </Prompt>

          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.
        </Step>
      </Steps>
    </Tab>

    <Tab title="VS Code">
      Send data with VS Code (with GitHub Copilot) by installing the Honeycomb MCP server and agent skills:

      <Steps>
        <Step title="Install the Honeycomb MCP">
          Use this one-click install link: [Add Honeycomb to VS Code](vscode:mcp/install?%7B%22name%22%3A%22honeycomb%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.honeycomb.io%2Fmcp%22%7D)
        </Step>

        <Step title="Install the agent skills">
          Copy the agent skills files from the [Honeycomb Agent Skills repo](https://github.com/honeycombio/agent-skill) into VS Code's skills directory.
          For setup steps, visit VS Code's [Agent Skills](https://code.visualstudio.com/docs/copilot/customization/agent-skills) documentation.
        </Step>

        <Step title="Onboard with Honeycomb">
          Run this prompt to start onboarding:

          <Prompt description="Begin Honeycomb onboarding" icon="sparkle">
            /honeycomb-onboarding
          </Prompt>

          Your agent starts guided onboarding against your live Honeycomb account, using sample data, real instrumentation, or data you are already sending.
        </Step>
      </Steps>
    </Tab>
  </Tabs>
</div>

## Next steps

* [Example Use Cases](/integrations/mcp/use-cases): Explore real-world use cases and tips for working with Honeycomb via MCP.
* [Tools Reference](/integrations/mcp/tools): Learn about the tools Honeycomb MCP exposes to AI agents.
* [Troubleshooting](/integrations/mcp/troubleshooting): Fix common MCP configuration and connection issues.