# Agentic Data Plane

> Index of Agentic Data Plane documentation pages. Each link points to the page's markdown version.
> For the full documentation index, see https://docs.redpanda.com/llms.txt

## Pages

- [Use the Agentic Data Plane CLI](https://docs.redpanda.com/agentic-data-plane/cli.md): Manage Agentic Data Plane resources from the terminal with rpk ai. Install the CLI, connect to an AI Gateway, and script providers, servers, agents, and triggers.
- [Manage Resources with GitOps](https://docs.redpanda.com/agentic-data-plane/cli/gitops.md): Keep Agentic Data Plane resources in Git and reconcile them with rpk ai apply and diff: declarative create-or-update, drift detection, and CI gating.
- [Connect Data & Tools](https://docs.redpanda.com/agentic-data-plane/connect.md): Connect agents, MCP servers, and the apps and data sources behind them.
- [Connect Agents with A2A](https://docs.redpanda.com/agentic-data-plane/connect/a2a-concepts.md): The A2A protocol lets agents discover and call each other across platforms. Learn how agent cards, authentication, and versioning work.
- [How Agents Work](https://docs.redpanda.com/agentic-data-plane/connect/agents-overview.md): Learn how Agentic Data Plane agents use a declarative approach backed by a broad library of prebuilt tools and integrations to replace custom agent code.
- [Build Agents](https://docs.redpanda.com/agentic-data-plane/connect/agents.md): Understand how AI agents work in the Agentic Data Plane, then create, register, and design them.
- [Choose an Agent Architecture](https://docs.redpanda.com/agentic-data-plane/connect/architecture-patterns.md): Design maintainable agent systems with single-agent and multi-agent patterns based on domain complexity.
- [Set Up Authentication](https://docs.redpanda.com/agentic-data-plane/connect/authentication.md): Configure OAuth providers, user-delegated OAuth, and client connections so agents and tools authenticate securely.
- [Chart Schema Reference](https://docs.redpanda.com/agentic-data-plane/connect/chart-schema-reference.md): Look up the inline chart types, JSON data shapes, validation rules, and size limits for agent responses.
- [Run Claude Code and Codex through AI Gateway](https://docs.redpanda.com/agentic-data-plane/connect/coding-agents.md): Launch Claude Code or Codex with rpk ai run, routing model traffic through a managed, enterprise-passthrough, Amazon Bedrock, or Vertex AI provider.
- [Understand Agent Concepts](https://docs.redpanda.com/agentic-data-plane/connect/concepts.md): Understand how declaratively configured agents execute reasoning loops, manage context, invoke tools, and handle errors.
- [Create an Agent](https://docs.redpanda.com/agentic-data-plane/connect/create-agent.md): Configure a managed Agentic Data Plane agent declaratively on a single create canvas. No Python or JavaScript code required.
- [Create an MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/create-server.md): Create an MCP server. Pick a managed type from the marketplace or register one you host, then configure authentication, code mode, and access.
- [Shape Tool Data with Data Policies](https://docs.redpanda.com/agentic-data-plane/connect/data-policies.md): Add data policies to an MCP server to mask, drop, or filter tool data, restrict argument values, and preview the effect before saving.
- [Draw Charts from an Agent](https://docs.redpanda.com/agentic-data-plane/connect/draw-charts.md): Configure an agent to draw inline charts, inspect their data, and troubleshoot invalid chart blocks in the Playground.
- [Set Up GitHub OAuth Provider and MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/github-oauth-tutorial.md): Complete walkthrough for configuring GitHub as an OAuth provider and creating a user-delegated GitHub MCP server.
- [Choose an Integration Pattern](https://docs.redpanda.com/agentic-data-plane/connect/integration-overview.md): Choose the right integration pattern for connecting agents, tools, and external applications.
- [Integrate with Your Stack](https://docs.redpanda.com/agentic-data-plane/connect/integrations.md): Choose an integration pattern and connect the Agentic Data Plane to your existing stack and developer tools.
- [BambooHR Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/bamboohr.md): Let agents read BambooHR employee, time-off, and performance data with each caller's BambooHR OAuth identity.
- [Exa Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/exa.md): Connect agents to Exa with per-user OAuth for web search, page contents, and research with an explicit per-run budget.
- [Freshservice Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/freshservice.md): Manage Freshworks Freshservice ITSM tickets, assets, change requests, and agents from an agent, with API-key or per-user OAuth authentication.
- [Grafana Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/grafana.md): Query Grafana dashboards, datasources, Prometheus metrics, and Loki logs from an agent, and create or update dashboards, using a service-account token.
- [Ironclad Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/ironclad.md): Read and manage contracts in Ironclad CLM. Per-user OAuth so each agent action runs as the calling end-user with their own Ironclad permissions.
- [JavaScript Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/javascript.md): Ship a custom MCP server by writing JavaScript. Redpanda runs your bundle in a sandbox and holds its requests to a host allowlist.
- [Jira Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/jira.md): Let agents search, read, and manage Jira issues using either a shared API token or each end-user's own Atlassian identity through user-delegated OAuth.
- [Plug in an App, Database, or Tool](https://docs.redpanda.com/agentic-data-plane/connect/managed/managed-catalog.md): Reference of every managed MCP server type Redpanda hosts, grouped by category, with descriptions and links to setup guides.
- [Metabase Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/metabase.md): Give an agent read-and-query access to Metabase through the semantic layer (search, metrics, query) and the native-SQL escape hatches.
- [NetSuite Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/netsuite.md): Let agents read NetSuite records and run SuiteQL with each caller's NetSuite OAuth identity.
- [Set Up Snowflake as an OpenAPI MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/openapi-snowflake.md): Connect the Snowflake SQL API to your agents with the OpenAPI managed MCP server and a Snowflake programmatic access token.
- [OpenAPI Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/openapi.md): Expose any HTTP API described by an OpenAPI 3.0 spec as MCP tools. Point Redpanda at a spec URL and get a fully-typed tool surface for agents, with no custom code.
- [Pylon Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/pylon.md): Connect agents to Pylon issues, accounts, contacts, and knowledge-base articles with a shared API token. Writes stay off until you enable them.
- [Ramp Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/ramp.md): Manage Ramp corporate cards, transactions, spend limits, and reimbursements from an agent, with per-user OAuth so each action runs as the end-user.
- [Salesforce Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/salesforce.md): Query, create, update, and delete Salesforce records with SOQL and the REST API, and run reports, using service-account or per-user OAuth.
- [Sentry Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/sentry.md): Give an agent read-only access to Sentry issues, events, and releases through per-user OAuth to read stack traces and scope an error's impact.
- [ServiceNow Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/servicenow.md): Read and write ServiceNow incidents, catalog requests, knowledge articles, and allow-listed records with service-account or per-user authentication.
- [SharePoint Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/sharepoint.md): Let agents read and search SharePoint sites, lists, and files through the Microsoft Graph API with each end-user's own identity (user-delegated OAuth).
- [Slack Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/slack.md): Let agents search Slack, find channels, read messages, post, and react, acting either as the Slack app or as the person who authorizes.
- [SQL Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/sql.md): Query and write to PostgreSQL databases through a managed MCP server hosted by Redpanda.
- [Zendesk Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/managed/zendesk.md): Search and manage Zendesk tickets, users, and Help Center articles. API token or per-user OAuth, plus token-efficient response shaping for agents.
- [How MCP Servers Work](https://docs.redpanda.com/agentic-data-plane/connect/mcp-overview.md): Connect AI agents to your databases, APIs, and business systems through managed MCP servers Redpanda hosts, or self-managed servers you register.
- [Connect Tools with MCP Servers](https://docs.redpanda.com/agentic-data-plane/connect/mcp-servers.md): Learn how MCP servers expose tools and data to agents, then plug in a managed type or build, register, and test your own.
- [Configure an OAuth Provider](https://docs.redpanda.com/agentic-data-plane/connect/oauth-providers.md): Register an OAuth provider so MCP servers can authenticate users or service accounts against an upstream system like Slack, Jira, or GitHub.
- [Register a Self-Managed MCP Server](https://docs.redpanda.com/agentic-data-plane/connect/register-remote.md): Front your own MCP server with a managed Redpanda URL. Pick a transport, configure authentication, and let agents discover its tools.
- [Connect Remote MCP Clients](https://docs.redpanda.com/agentic-data-plane/connect/remote-mcp-clients.md): Connect external MCP clients to MCP servers in AI Gateway using client metadata documents, dynamic client registration, or manual registration.
- [Set Up a Self-Managed Agent](https://docs.redpanda.com/agentic-data-plane/connect/self-managed-agents.md): Register a self-managed agent, issue it a client credential, and route its LLM and tool calls through the AI Gateway for spend, traces, and transcripts.
- [Self-Managed Agent Telemetry Reference](https://docs.redpanda.com/agentic-data-plane/connect/self-managed-telemetry.md): The OTLP endpoint, span contract, ingestion limits, and validation checks for streaming transcripts from a self-managed agent.
- [Write Effective System Prompts](https://docs.redpanda.com/agentic-data-plane/connect/system-prompts.md): Write system prompts that produce reliable, predictable agent behavior through clear constraints and tool guidance.
- [Test an MCP Server’s Tools with the Inspector](https://docs.redpanda.com/agentic-data-plane/connect/test-tools.md): Use the Inspector tab to call tools, inspect resources and prompts, and verify your MCP server works without standing up an agent.
- [Connect an Agent to Microsoft Teams](https://docs.redpanda.com/agentic-data-plane/connect/triggers/microsoft-teams.md): Add a Microsoft Teams trigger to a deployed agent so people in your organization can chat with it in a personal Teams chat.
- [Trigger Agents](https://docs.redpanda.com/agentic-data-plane/connect/triggers/overview.md): Triggers invoke a deployed agent without calling its API directly, from Microsoft Teams or on a schedule.
- [Run an Agent on a Schedule](https://docs.redpanda.com/agentic-data-plane/connect/triggers/schedule.md): Add a schedule trigger to a deployed agent so it runs automatically on a recurring cron schedule, in the timezone you choose.
- [Use an MCP Server from an AI Client](https://docs.redpanda.com/agentic-data-plane/connect/use-server-from-ai-client.md): Add an MCP server hosted in Agentic Data Plane to Claude, Claude Code, Cursor, or another AI client, sign in, and start calling its tools.
- [Configure User-Delegated OAuth](https://docs.redpanda.com/agentic-data-plane/connect/user-delegated-oauth.md): Have each end-user authenticate to the upstream system with their own credentials. Redpanda stores their token and injects it at call time.
- [Control & Govern](https://docs.redpanda.com/agentic-data-plane/control.md): Govern agent activity with guardrails, spend limits, and permissions.
- [Manage Access Policies](https://docs.redpanda.com/agentic-data-plane/control/access-policies.md): Create Cedar-based access policies that permit or forbid specific actions in the Agentic Data Plane, with conditions over resource tags and ownership.
- [Manage Access](https://docs.redpanda.com/agentic-data-plane/control/access.md): Control who can do what in the Agentic Data Plane with access policies.
- [Set Up Budgets](https://docs.redpanda.com/agentic-data-plane/control/budgets.md): Cap LLM spend with per-agent budgets, and see what the Agentic Data Plane records automatically and where to view it.
- [Track Spend by Tag](https://docs.redpanda.com/agentic-data-plane/control/cost-allocation-tags.md): Group LLM spend by the tags you set on agents, so you can attribute cost to a department, team, or environment for chargeback and reporting.
- [Analyze Cost and Usage](https://docs.redpanda.com/agentic-data-plane/control/cost-usage.md): Read LLM spend against the previous period, break it down by agent, model, provider, user, or tag, and export the report as CSV.
- [Set Up Guardrails](https://docs.redpanda.com/agentic-data-plane/control/guardrails.md): Understand how guardrails work, create them, review blocked requests, and look up the available policies.
- [Create a Guardrail](https://docs.redpanda.com/agentic-data-plane/control/guardrails/create-guardrail.md): Create a guardrail, configure its policies on the guardrail's own page, attach it to an LLM provider, and verify that it blocks.
- [How Guardrails Work](https://docs.redpanda.com/agentic-data-plane/control/guardrails/overview.md): Learn how Agentic Data Plane guardrails use Amazon Bedrock policies to inspect and control LLM requests and responses, and how a blocked request surfaces.
- [Guardrail Policy Reference](https://docs.redpanda.com/agentic-data-plane/control/guardrails/types-reference.md): Reference for the guardrail policy types, their configuration fields, actions, directions, and limits.
- [Review Blocked Requests](https://docs.redpanda.com/agentic-data-plane/control/guardrails/violations.md): Understand how a blocked request surfaces, where guardrail activity is recorded, and what to check when a guardrail blocks too much or too little.
- [Control Who Can Do What](https://docs.redpanda.com/agentic-data-plane/control/permissions-overview.md): Understand how Agentic Data Plane decides who can do what: access policies carry the decision, and RBAC bootstraps the administrators who author them.
- [Roles and Permissions Reference](https://docs.redpanda.com/agentic-data-plane/control/permissions-reference.md): Look up the permissions Agentic Data Plane enforces across LLM providers, MCP servers, agents, access policies, and governance APIs.
- [AI Gateway & LLM Providers](https://docs.redpanda.com/agentic-data-plane/gateway.md): Configure AI Gateway, the proxy between your agents and LLM providers such as OpenAI, Anthropic, Google Gemini API, and Amazon Bedrock, then connect your apps to it.
- [Set Up Amazon Bedrock as an LLM Provider](https://docs.redpanda.com/agentic-data-plane/gateway/bedrock-setup.md): Create the IAM user, policy, and access keys required for AI Gateway to invoke Amazon Bedrock models, then register the provider in Agentic Data Plane.
- [Code Mode](https://docs.redpanda.com/agentic-data-plane/gateway/code-mode.md): Turn on code mode for an MCP server to replace a large tool catalog with two tools, search and execute, and cut the token cost of tool-heavy servers.
- [Configure an LLM Provider](https://docs.redpanda.com/agentic-data-plane/gateway/configure-provider.md): Create an LLM provider to proxy requests to OpenAI, Anthropic, Google Gemini API, Amazon Bedrock, or any OpenAI-compatible endpoint through Agentic Data Plane.
- [Connect Your App to AI Gateway](https://docs.redpanda.com/agentic-data-plane/gateway/connect-agent.md): Point your app or AI agent at an AI Gateway proxy URL. Authenticate with rpk ai, OIDC client credentials, or an API key, then send requests with your SDK.
- [How AI Gateway Works](https://docs.redpanda.com/agentic-data-plane/gateway/overview.md): AI Gateway is Agentic Data Plane's managed proxy for LLM APIs. Each provider gets a Redpanda-hosted URL with secrets, authentication, and observability.
- [Get Started](https://docs.redpanda.com/agentic-data-plane/get-started.md): Stand up Redpanda Agentic Data Plane and ship your first agent.
- [Redpanda Agentic Data Plane Overview](https://docs.redpanda.com/agentic-data-plane/get-started/adp-overview.md): Enterprise-grade infrastructure for building, deploying, and governing AI agents at scale with compliance-grade audit trails.
- [Agentic Data Plane Quickstart for Administrators](https://docs.redpanda.com/agentic-data-plane/get-started/adp-quickstart.md): Set up Redpanda Agentic Data Plane for your organization. Configure an LLM provider, verify it, and hand off to your agent builders.
- [Agentic Data Plane Quickstart for Agent Builders](https://docs.redpanda.com/agentic-data-plane/get-started/agent-builder-quickstart.md): Sign in to Redpanda Agentic Data Plane, explore the agents your organization runs, then build and test your own agent backed by MCP tools.
- [Create an Agentic Data Plane Environment](https://docs.redpanda.com/agentic-data-plane/get-started/create-environment.md): Create an Agentic Data Plane environment in your AWS account or Google Cloud project using the Redpanda Cloud UI and CLI.
- [Agentic Data Plane Learning Path](https://docs.redpanda.com/agentic-data-plane/get-started/learning-path.md): Read the Agentic Data Plane docs in an order that builds from platform concepts to a running agent, governance controls, and production integration.
- [Monitor & Debug](https://docs.redpanda.com/agentic-data-plane/monitor.md): See what your agents did, investigate runs, and check speed, cost, and errors.
- [Visualize Your Agent Network](https://docs.redpanda.com/agentic-data-plane/monitor/agent-network.md): See a live map of your agents, the models they call, and the MCP servers they use, with usage, cost, and health for a chosen time window.
- [Review the Audit Log](https://docs.redpanda.com/agentic-data-plane/monitor/audit-log.md): Review authorization decisions across Agentic Data Plane in the UI or with rpk ai, filter them, and see who acted on which resource and whether the request was allowed.
- [How Observability Works](https://docs.redpanda.com/agentic-data-plane/monitor/concepts.md): Understand how Redpanda captures end-to-end execution transcripts on an immutable distributed log for agent governance and observability.
- [Monitor Agent Activity](https://docs.redpanda.com/agentic-data-plane/monitor/monitor-agents.md): Monitor agent execution, inspect available MCP tools, analyze conversation history, track token usage, and debug issues using Playground and Transcripts.
- [Trace an Agent Run](https://docs.redpanda.com/agentic-data-plane/monitor/traces.md): Read one row per agent run or AI Gateway call, expand it into a span waterfall, and find the LLM call, tool call, or policy decision behind a slow or failed run.
- [See What Your Agent Did](https://docs.redpanda.com/agentic-data-plane/monitor/transcripts.md): Open a transcript in Agentic Data Plane, read the conversation turn by turn, and investigate errors and performance.
- [Troubleshoot Agents](https://docs.redpanda.com/agentic-data-plane/monitor/troubleshoot-ai-agents.md): Diagnose and fix common issues with AI agents, including MCP server connection failures, gateway errors, runtime behavior problems, and tool execution errors.
- [Reference](https://docs.redpanda.com/agentic-data-plane/reference.md): Field and command reference for Agentic Data Plane.