Agentic Data Plane

Redpanda ADP Quickstart

This quickstart sets up Redpanda ADP from scratch and follows the two roles involved:

  • An administrator configures a large language model (LLM) provider for your organization. This is a one-time setup task. Until a provider exists, no one can build agents against it.

  • Builders then create MCP servers and agents that use the configured provider.

Administrators complete the Admins: Configure an LLM provider section, and builders complete the Builders: Create an MCP server and agent section. If you have the Admin role, you can complete both yourself. If your administrator has already configured an LLM provider, skip to Builders: Create an MCP server and agent.

When you sign in to ADP at ai.redpanda.com, you land on the Home page: a snapshot of items that need your attention, recent request and spend activity, budget status, and counts of your ADP resources. Start the tasks in this guide from the sidebar.

After reading this page, you will be able to:

  • Configure your first LLM provider in ADP with an Anthropic API key

  • Create an MCP server from a public OpenAPI spec

  • Build an agent that calls both the LLM provider and the MCP server

Prerequisites

The built-in role you need depends on which sections you complete. The Reader role can list resources but cannot create them.

For admins

This quickstart configures an Anthropic provider, but ADP also supports OpenAI, Google AI, AWS Bedrock, and OpenAI-compatible endpoints. To set up the Anthropic provider, you need:

For builders

To create an MCP server and agent:

  • The Writer role in ADP.

  • At least one LLM provider configured in your organization. If none exists, complete the admin steps first, or ask your administrator.

What you build

You create the following ADP resources, in order:

  1. Anthropic LLM provider (administrator). Routes Claude API calls through ADP so credentials, usage, and transcripts stay on the platform.

  2. PetStore MCP server (builder). Exposes the public Swagger PetStore API as a set of MCP tools the agent can call.

  3. Pet store assistant agent (builder). Combines the provider and the MCP server so a natural-language question becomes a real API call against PetStore.

After the agent works, you can walk through one execution turn-by-turn in the Transcripts view.

Admins: Configure an LLM provider

A provider is an organization-level resource. Configure it once, and every builder can select it when they create agents. The following sections walk through getting an Anthropic API key and pointing ADP at Anthropic.

Get an Anthropic API key

Anthropic requires a payment method before it issues an API key. Add billing first, then create the key.

  1. Open platform.claude.com and sign in, or create a new account.

  2. Add a payment method to your account if you haven’t already. Anthropic requires a payment method before it issues API keys. (Optional: add a small amount of prepaid credit so the quickstart calls don’t fail on a fresh account.)

  3. In the sidebar, select a workspace other than Claude Code. The Claude Code workspace uses a separate key-creation flow that doesn’t fit this quickstart.

  4. Click API keys in the sidebar.

  5. Click + Create key in the top right. In the Create API key dialog, name the key adp-quickstart and click Add.

  6. Copy the key (it starts with sk-ant-).

    Anthropic shows the API key value once. If you close the dialog without copying, you can’t recover it. Paste the key into a secure note before continuing. The next section creates the secret in ADP’s secret store as part of the provider form, so you don’t have to keep the key on your local machine.

  7. (Optional) On the API keys page, confirm the new key appears in the list.

Configure your LLM provider

Now point ADP at Anthropic. ADP references provider credentials by secret name, not by raw value, and you create the secret inline as part of this form.

  1. Sign in to ADP at ai.redpanda.com.

  2. Open LLM Providers in the sidebar.

  3. Click Create provider.

  4. Display name: Enter anthropic-quickstart. This label appears in dashboards and model selectors.

  5. Leave the auto-derived Resource ID. ADP generates it from the display name, using lowercase letters, numbers, and hyphens. The ID is used in API calls and CLI commands and can’t be changed after creation.

  6. Provider type: Select Anthropic.

  7. API key reference: Switch to the New tab and create the secret inline:

    • Name the secret ANTHROPIC_API_KEY. ADP uppercases the name automatically, and you can’t change it after creation.

    • Under Secret value, leave the Text tab selected and paste the sk-ant- key you copied from Anthropic.

    • Click Create secret.

      The secret value is write-only: ADP can’t show it again after creation, so if you mistype the key, create a new secret. New secrets get the AI Gateway scope automatically, which makes them usable across the platform: LLM providers, MCP servers, and agents. To create secrets ahead of time or manage them later, open Secrets Store in the sidebar.

  8. Leave Authorization passthrough off. This quickstart uses one shared key, not per-user OAuth.

  9. Leave the default Base URL in place. The form prefills the standard Anthropic endpoint.

  10. Models: Select these models from the catalog:

    • claude-haiku-4-5 (fast and inexpensive, good for testing)

    • claude-sonnet-4-6 (higher quality, better tool use, used by the agent in the next sections)

      The catalog of available models is maintained by Redpanda. Models you select here become the catalog this provider exposes to agents and applications; you can change the list later from the provider detail page.

  11. Click Create provider.

  12. On the provider detail page, confirm the badge next to the provider name shows Enabled and the Status in the Connection card shows Active.

If the Status badge stays in a failure state, see the provider troubleshooting table. The most common cause is a typo in the secret reference or a key that wasn’t issued in the workspace ADP can read.

For the full provider field reference (transcript logging, Bedrock IAM, Anthropic authentication passthrough, OpenAI-compatible endpoints), see Configure an LLM provider.

Builders: Create an MCP server and agent

With a provider in place, a builder creates a tool server and an agent that uses it. Both are configured in the UI: the server from a marketplace picker, the agent on a single configuration page.

If your administrator has already configured an LLM provider, you can skip the provider setup and start here. Select the existing provider in the agent form’s Model section.

Create an MCP server with a public OpenAPI spec

The OpenAPI managed MCP server type takes any OpenAPI 3.x spec URL and generates one MCP tool per operation. You point it at the public Swagger PetStore, which exposes a small pet-inventory API with no authentication.

PetStore is a public demo that Swagger hosts for testing and is occasionally unavailable. If your agent later returns an HTTP 500 from PetStore, that’s the upstream, not ADP. Retry the prompt, or move on to a real MCP server (Managed MCP catalog) after you’ve confirmed the rest of the flow works.

  1. Open MCP Servers in the sidebar and click Create server.

  2. Search for and select the OpenAPI card from the marketplace picker.

    The Create MCP Server marketplace picker filtered by a search for openAPI

  3. Name: Enter petstore-quickstart.

  4. Description: Enter Public PetStore API exposed as MCP tools for quickstart testing. Optional, but helps you find the server later.

  5. Leave the Code mode toggle off. Code mode adds search and execute tools that let agents run sandboxed code against the server’s tools. The PetStore catalog is small enough that you don’t need it for this quickstart.

  6. Spec: Enter https://petstore3.swagger.io/api/v3/openapi.json.

  7. Base URL override: Leave blank. The PetStore spec already declares the right servers block, so no override is needed.

  8. Skip all other optional configuration fields.

  9. For the authentication mode, select None. PetStore is a public API.

  10. Click Create.

  11. Redpanda fetches the spec, parses it, and generates one MCP tool per operation. When the server is ready, open its detail page.

  12. On the Overview tab, copy the API URL. This is the MCP URL the agent connects to.

  13. Open the Inspector tab. Redpanda runs a live tools/list against the server and lists every tool it discovered. Confirm the list includes findpetsbystatus, getpetbyid, findpetsbytags, and addpet. The OpenAPI MCP server lowercases tool names when it generates them from the spec’s operationId values.

    The exact tool count depends on the operations defined in the spec at fetch time. A populated list confirms the connection works. If the list is empty or the tab shows an error, see OpenAPI MCP troubleshooting.

For the full OpenAPI MCP reference (authentication modes, operation filters, base URL overrides), see OpenAPI managed MCP server.

Build your agent

Combine the Anthropic provider and the PetStore MCP server into an agent. ADP configures a managed agent on a single page with five sections: Details, Model, Behavior, Tools, and Subagents. A stepper on the left tracks the sections and summarizes what you’ve set in each; click a step to jump to its section. For the full reference, see Create an agent.

  1. Open Agents in the sidebar.

  2. Click Create agent.

  3. Choose how the agent runs. Click Redpanda manages it, so Redpanda deploys, runs, and observes the agent for you.

    The runtime choice in the create-agent flow
    The other option, I host it myself, registers an agent you run on your own infrastructure. This quickstart uses the managed runtime.

  4. In the Details section, set the following:

    • Agent ID: Skip for now. ADP pre-fills a generated ID and re-derives it from the display name you enter next. You can’t change the ID after creation.

    • Display name: Enter pet-store-assistant. This name appears in the agent registry list and the detail header, and the Agent ID updates to match.

    • Description: Enter Quickstart agent that answers questions about the PetStore inventory.

    • Tags: Skip. Tags are optional metadata for filtering and grouping.

  5. In the Model section, set the following:

    • LLM provider: Select anthropic-quickstart. This provider supplies the credentials and routing for the agent. The dropdown lists every provider configured for your organization. If it’s empty, no provider exists yet. Ask your administrator to configure one, or complete the admin steps first.

    • Model: Select claude-sonnet-4-6. Sonnet handles multi-step tool use more reliably than Haiku.

      Leave the Advanced options, such as Max iterations, at their defaults.

  6. In the Behavior section, paste the following into the System prompt editor:

    You are a pet store inventory assistant.

You have access to PetStore API tools through MCP. Use them to answer
questions about pets. The most useful read tools are:
- findpetsbystatus: List pets by status (available, pending, sold)
- getpetbyid: Look up a specific pet by ID
- findpetsbytags: Search by tag

Rules:
- Always call a tool before answering. Don't make up pet data.
- After each tool call, summarize what the tool returned and cite the
  tool name in your response.
- If a tool fails or returns no data, say so and stop. Don't retry
  with invented IDs.
- Stick to read operations for this quickstart. Don't add, update, or
  delete pets.

  7. In the Tools section, select petstore-quickstart under MCP servers. The agent discovers the server’s tools at runtime; you don’t pre-select individual tools. The system prompt’s "stick to read operations" rule constrains behavior. You can change this list at any time.

  8. In the Subagents section, leave the list empty to keep the agent flat. The quickstart uses a single agent.

  9. Confirm the stepper summaries on the left, then click Create agent. If a required field is missing, a "Cannot create agent" error lists what to fix.

  10. Wait for the agent status to change from Starting to Running. ADP creates the agent’s service account at this point; for details, see service account authorization.

Test the agent in the Inspector

The Inspector tab is a chat surface for the agent. Type a prompt into the input at the bottom of the page and click the paper-plane icon in the input’s bottom-right corner to send. Each prompt creates a Task card in the conversation that walks through the agent’s execution turn-by-turn: TaskStatusUpdate entries (Submitted → Working → Completed) with token counts, individual tool-call cards showing the tool name and latency, and an Artifact card holding the final response. Clear context (at the bottom of the input) resets the conversation between tests.

  1. On the agent detail page, open the Inspector tab.

  2. Send the first prompt:

    What pets are available right now?

    The agent calls findpetsbystatus with status=available and returns a summary of the pets, naming the tool. This PetStore endpoint is occasionally flaky; if it returns an HTTP 500, retry the prompt. The public PetStore is occasionally down.

  3. (Optional) Send an open-ended prompt to confirm multi-step reasoning:

    Find a pet tagged "friendly" and tell me whether it's available.

    The agent may call findpetsbytags first, then getpetbyid for one of the matches, then summarize.

If the agent hallucinates data instead of calling a tool, tighten the system prompt’s "Always call a tool before answering" rule. See system prompt best practices for patterns.

If a tool card shows an HTTP 500 error and the Artifact apologizes about the pet store API being unavailable, that’s the public Swagger PetStore being intermittently down. The agent is behaving correctly (the "if a tool fails, say so and stop" rule in the system prompt is what produced the apology). Retry the prompt; PetStore usually recovers within a few minutes.

Iterate on your agent

Agent configuration isn’t fixed after you create it. Edit the system prompt or model, save, and re-test in the Inspector to see how behavior changes.

  1. On the agent detail page, open the Overview tab. The tab shows the agent’s full configuration as an editable form.

  2. Adjust the System prompt to change how the agent responds. For example:

    • Add a constraint: Never call more than one tool per response.

    • Change the output format: Always format pet details as a bulleted list.

    • Add a confirmation step: Before answering, restate which tool you plan to call and why.

  3. Click Save changes.

  4. Open the Inspector tab, click Clear context, and re-send one of the earlier prompts to compare the agent’s behavior against your change.

For system prompt patterns and anti-patterns, see Write effective system prompts.

Clean up

If this is a one-off quickstart, delete the resources you created so they don’t continue to count against your account.

  1. Delete the agent (pet-store-assistant) first. Open the agent detail page, scroll to the delete section, and click Delete.

  2. Delete the MCP server (petstore-quickstart). Same pattern.

  3. Delete the LLM provider (anthropic-quickstart). Same pattern. Note that the underlying secret (ANTHROPIC_API_KEY) is not deleted automatically.

  4. (Optional) Delete the secret. Open Secrets Store, click ANTHROPIC_API_KEY, then Delete.

  5. (Optional, on the Anthropic side) Revoke the API key. Open platform.claude.com, navigate to Manage > API keys in the workspace where you created the key, find adp-quickstart in the list, and revoke it from the row’s action menu.

If you want to keep the provider but rotate the key, edit the provider and change the API key reference to a new secret.

Next steps