# Home - Full Markdown Export > This file contains all Home documentation pages in markdown format for AI agent consumption. > Generated from 3 pages on 2026-10-14T15:42:46.323Z > Component: home | Version: > Site: https://docs.redpanda.com ## About This Export This export includes the **latest version** () of the Home documentation. ### AI-Friendly Documentation Formats We provide multiple formats optimized for AI consumption: - **https://docs.redpanda.com/llms.txt**: Curated overview of all Redpanda documentation - **https://docs.redpanda.com/llms-full.txt**: Complete documentation export with all components - **https://docs.redpanda.com/home-full.txt**: This file - Home documentation only - **Individual markdown pages**: Each HTML page has a corresponding .md file --- # Page 1: Welcome to Redpanda Documentation **URL**: https://docs.redpanda.com/home.md --- --- title: Welcome to Redpanda Documentation latest-operator-version: v26.2.4 latest-console-tag: v3.12.0 latest-connect-version: 4.113.0 latest-redpanda-tag: v26.2.4 docname: index page-component-name: home page-version: master page-component-version: master page-component-title: Home page-relative-src-path: index.adoc page-edit-url: https://github.com/redpanda-data/docs-site/edit/HEAD/home/modules/ROOT/pages/index.adoc description: Redpanda is a high-performance streaming data platform and Agentic Data Plane. Kafka API-compatible, it enables real-time data streaming, event-driven architectures, and AI agent governance and observability. page-git-created-date: "2023-06-12" page-git-modified-date: "2026-08-07" --- Redpanda Documentation # Everything you need to move data and put agents to work on it. Guides, concepts, and references for the two platforms that power Redpanda: streaming your data reliably and letting AI agents act on it safely. Try: How do I connect Salesforce as an MCP source? Set a monthly token budget Deploy Redpanda on Kubernetes ## What are you here for ### Build agentic data flows Build, connect, and govern AI agents on top of your data. Create agents without code, plug in Salesforce or your database, and keep every action observable and in-policy. [Get started](https://docs.redpanda.com/agentic-data-plane/get-started/adp-quickstart/) [Documentation](https://docs.redpanda.com/agentic-data-plane/home/) ### Stream and process data Run Redpanda clusters, move data reliably between systems, and keep storage lean with Tiered Storage and connectors. Data Platform [ Cloud Streaming, Connect, and SQL with Serverless or BYOC deployment ](https://docs.redpanda.com/cloud-data-platform/home/) [Self-Managed](https://docs.redpanda.com/self-managed/)[](../self-managed/) Deploy on your infrastructure [ Streaming v26.2 Redpanda broker and rpk CLI ](https://docs.redpanda.com/self-managed/)[ Connect Data pipelines and transformations ](https://docs.redpanda.com/connect/home/) --- # Page 2: How to Use These Docs **URL**: https://docs.redpanda.com/home/how-to-use-these-docs.md --- # How to Use These Docs --- title: How to Use These Docs latest-operator-version: v26.2.4 latest-console-tag: v3.12.0 latest-connect-version: 4.113.0 latest-redpanda-tag: v26.2.4 docname: how-to-use-these-docs page-component-name: home page-version: master page-component-version: master page-component-title: Home page-relative-src-path: how-to-use-these-docs.adoc page-edit-url: https://github.com/redpanda-data/docs-site/edit/HEAD/home/modules/ROOT/pages/how-to-use-these-docs.adoc description: Navigate Redpanda's documentation structure and leverage AI-powered features including MCP server integration, markdown exports, and interactive documentation tools. page-git-created-date: "2026-06-15" page-git-modified-date: "2026-09-18" --- Redpanda’s documentation helps you stream data, build pipelines, and deploy AI agents whether you manage infrastructure yourself or run in the cloud. This page explains how our docs are organized, clarifies the relationship between deployment models and products, and shows you how to access documentation through AI-powered tools and programmatic interfaces. ## [](#understand-the-documentation-structure)Understand the documentation structure Redpanda’s documentation is organized around multiple deployment models and products. The Data Platform provides the streaming foundation with Cloud or Self-Managed deployment options. The Agentic Data Plane offers a specialized infrastructure for AI agents and agentic workflows. Documentation hierarchy Redpanda Documentation ├── Data Platform │ ├── Cloud (managed by Redpanda) │ │ ├── Serverless │ │ ├── BYOC │ │ └── Dedicated │ └── Self-Managed (managed by you) │ ├── Streaming (broker, Redpanda CLI) │ └── Connect (data pipelines) └── Agentic Data Plane └── AI agent infrastructure and workflows > 📝 **NOTE** > > **What changed:** Previously, the software that deployed a Redpanda broker was called "Redpanda Self-Managed". In the new structure, "Self-Managed" refers to the deployment model (you manage the infrastructure), while "Streaming" is the product name for the broker itself. **Key components:** - [Data Platform overview](https://docs.redpanda.com/data-platform/): The streaming foundation - [Self-Managed documentation](https://docs.redpanda.com/self-managed/): Deploy and manage yourself - [Streaming documentation](https://docs.redpanda.com/streaming/current/home/): Broker and Redpanda CLI - [Connect documentation](https://docs.redpanda.com/connect/home/): Data pipelines and integration - [Cloud documentation](https://docs.redpanda.com/cloud-data-platform/home/): Fully managed services - [Agentic Data Plane](https://docs.redpanda.com/agentic-data-plane/home/): AI agent infrastructure ## [](#choose-your-path)Choose your path Find the documentation that matches your use case: **I want to deploy Redpanda myself** → Self-Managed docs - Install and manage Redpanda Streaming and Connect on your own infrastructure - [Streaming quickstart](https://docs.redpanda.com/streaming/current/get-started/quick-start/) - [Connect quickstart](https://docs.redpanda.com/connect/get-started/quickstarts/rpk/) **I want Redpanda managed for me** → Cloud docs - Fully managed service with Serverless, BYOC, and Dedicated options - [Get started with Cloud](https://docs.redpanda.com/cloud-data-platform/home/) **I want to integrate data sources/sinks** → Connect docs - Available in both Cloud and Self-Managed deployments - Hundreds of prebuilt connectors including AI and change data capture (CDC) - [Connect documentation](https://docs.redpanda.com/connect/home/) **I want to build AI agent infrastructure** → Agentic Data Plane docs - Specialized platform for agentic workflows and AI agent orchestration - [Get started with the Agentic Data Plane](https://docs.redpanda.com/agentic-data-plane/home/) ## [](#ai-agent-access)AI agent access Redpanda’s documentation is optimized for AI agents and LLM consumption. Whether you’re building AI agents, IDE plugins, or automation tools, you can access documentation through interactive page features, a Model Context Protocol (MCP) server for real-time queries, and static markdown exports for offline processing. ### [](#discovery-files)Discovery files Redpanda follows the [llms.txt standard](https://llmstxt.org/) for AI agent discovery: - `[https://docs.redpanda.com/llms.txt](https://docs.redpanda.com/llms.txt)`: AI agent discovery file with curated overview and links to comprehensive resources - `[https://docs.redpanda.com/llms-full.txt](https://docs.redpanda.com/llms-full.txt)`: Every component in one file, using the latest version of each - Component-specific exports, which are smaller and cheaper to index than the full export: `streaming-full.txt`, `cloud-data-platform-full.txt`, `connect-full.txt`, `agentic-data-plane-full.txt`, `labs-full.txt`, and `home-full.txt` Older product versions are not in these exports. To get an older version, request the individual page instead (replace `.html` with `.md` in any URL). ### [](#page-options)Page options Every documentation page includes interactive features: **View as plain text:** Click **View as plain text** in the page options dropdown to render the current page in GitHub-Flavored Markdown format. This option is useful for reading in markdown-aware editors, accessing content offline, or sharing documentation snippets. **Copy as Markdown:** Click **Copy as Markdown** in the page options dropdown to copy the page markdown to your clipboard with YAML frontmatter preserved (includes title, description, git dates, categories, and more). This option is useful for pasting into notes, documentation systems, or issue trackers. **Ask AI:** Click **Ask AI** in the page options dropdown or top-nav section to open an AI chat drawer with full access to Redpanda documentation. The AI can explain configurations in simpler terms, show examples, or highlight common pitfalls. Without signing in, you can ask three questions every 24 hours. Sign in with a free Redpanda Cloud account for unlimited questions and the docs AI agent, which also saves your conversations. ### [](#install-the-mcp-server)Install the MCP server Redpanda provides a remote [Model Context Protocol (MCP) server](https://modelcontextprotocol.io) that lets you access authoritative Redpanda documentation directly from your IDE or AI tool, such as Claude Code, Cursor, VS Code, ChatGPT, or Claude Desktop. The MCP server is hosted at: `[https://docs.redpanda.com/mcp](https://docs.redpanda.com/mcp)`. You can add this endpoint to any AI agent that supports MCP. #### [](#authentication)Authentication You can connect and start asking without signing in. Anonymous access is limited to **10 tool calls every 24 hours**, counted per network address, so you share that allowance with anyone else using the server from the same network. Connecting and listing tools don’t count against it: only the tool calls your agent actually makes. Signing in with a [Redpanda Cloud account](https://cloud.redpanda.com/?utm_source=docs&utm_medium=referral&utm_campaign=docs-signup&utm_content=how-to-use-docs), which is [free to create](https://cloud.redpanda.com/sign-up?utm_source=docs&utm_medium=referral&utm_campaign=docs-signup&utm_content=how-to-use-docs), removes that limit, gives you an allowance of your own instead of a shared one, and enables the feedback tool. There’s no token to copy: the server uses OAuth, and any client that supports the MCP OAuth flow handles sign-in for you. You sign in once. Your client renews access in the background, and prompts you again only if you go 30 days without using the server. > ❗ **IMPORTANT** > > **Your client may not offer to sign you in.** MCP clients start their sign-in flow when a server tells them authentication is required, and this server doesn’t, because anonymous access works. So if you want the higher allowance, ask your client to authenticate rather than waiting to be prompted: reconnect the server, or use your client’s own authenticate action for it if it has one. > > Signing in to [docs.redpanda.com](https://docs.redpanda.com/login) in a browser is not enough on its own. That signs in the browser; your client authenticates separately, with its own OAuth flow. What signing in first **does** do is make that flow a redirect with nothing to click, which matters for the timing problem below. > 📝 **NOTE** > > If you connect through a `stdio` bridge such as `mcp-remote`, sign in to [docs.redpanda.com](https://docs.redpanda.com/login) in your default browser **before** you connect. Your client opens the browser for the sign-in step and waits a limited time for the result, and the host stops the bridge when its startup timeout elapses (30 seconds in Claude Code), taking the browser step with it. Creating a Cloud account takes longer than that. If you’ve already hit this, see [Sign-in opens a browser but the page fails to load](#client-sign-in-window). > 📝 **NOTE** > > **What we collect and why.** > > **When you sign in:** we receive your verified email address (and your organization, when available) from Redpanda Cloud, which we use to track documentation usage and attribute it to your organization. This may be shared with our customer and analytics systems and passed to our documentation search provider (Kapa) for usage attribution. > > **When you use Ask AI without signing in:** we count your free questions. Where your cookie choices allow it, we do that with a first-party cookie (`__Host-rp_docs_visitor`) holding a random identifier: it expires after 24 hours, holds nothing but that identifier, and is not shared with third parties. If you’ve declined that category in **Cookie preferences**, we store nothing on your device and count against your network address instead, which means you share that day’s free questions with others on the same network. > > **Either way:** so that starting fresh isn’t an unlimited reset, we keep a short-lived count per network address. Those counts are never tied to your questions or to you, and we don’t keep the address itself alongside them. > > For details, see our [Privacy Policy](https://www.redpanda.com/legal/privacy-policy). ##### Claude Code Run the following command to add the Redpanda MCP server to Claude Code: ```bash claude mcp add --scope user --transport http redpanda https://docs.redpanda.com/mcp ``` The server works straight away, on the anonymous allowance. To sign in for the higher allowance, run `/mcp` in Claude Code and authenticate the `redpanda` server. This adds the server as `redpanda` over the native HTTP transport, for your user account on any platform (stored in `~/.claude.json`). To verify the installation: ```bash claude mcp list ``` You should see `redpanda: [https://docs.redpanda.com/mcp](https://docs.redpanda.com/mcp) (HTTP): ✓ Connected` in the output. For more information about Claude Code, see the [Claude Code documentation](https://code.claude.com/docs/en/mcp). ##### Cursor Add the following to your `.cursor/mcp.json` file: ```json { "mcpServers": { "redpanda": { "type": "http", "url": "https://docs.redpanda.com/mcp" } } } ``` The server works straight away, on the anonymous allowance. To sign in for the higher allowance, reconnect the server from Cursor’s MCP settings. For more information about MCP in Cursor, see the [Cursor documentation](https://docs.cursor.com/context/model-context-protocol). ##### VS Code **Prerequisites:** VS Code 1.102+ with GitHub Copilot enabled. Create an `mcp.json` file in your workspace `.vscode` folder: `.vscode/mcp.json` ```json { "servers": { "redpanda": { "type": "http", "url": "https://docs.redpanda.com/mcp" } } } ``` The server works straight away, on the anonymous allowance. To sign in for the higher allowance, reconnect the server from the MCP view. To configure globally for all workspaces: 1. Open Command Palette (Cmd+Shift+P / Ctrl+Shift+P) 2. Run **MCP: Open User Configuration** 3. Add the same JSON configuration **Using MCP in VS Code:** 1. Open the Chat view (Ctrl+Cmd+I / Ctrl+Alt+I). 2. Select **Agent mode** from the dropdown. 3. Click the **Tools** button to see available MCP tools. 4. Ask questions about Redpanda and the AI automatically uses the documentation. For more details, see the [VS Code MCP documentation](https://code.visualstudio.com/docs/copilot/customization/mcp-servers). ##### ChatGPT Desktop ChatGPT Desktop supports MCP servers in developer mode. To enable: 1. Open ChatGPT Desktop. 2. Go to **Settings** > **Features**. 3. Enable **Developer mode**. 4. Navigate to **Settings** > **MCP Servers**. 5. Click **Add Server** and enter: - **Name**: `redpanda` - **URL**: `[https://docs.redpanda.com/mcp](https://docs.redpanda.com/mcp)` - **Authentication**: **OAuth** The server works straight away, on the anonymous allowance. ChatGPT can discover the OAuth flow when you reconnect the connector, which signs you in for the higher allowance. For more information, see the [ChatGPT Desktop MCP documentation](https://platform.openai.com/docs/guides/developer-mode). ##### Claude Desktop Connect Claude Desktop to Redpanda’s MCP server using one of two methods: **Method 1: Using Connectors** This method is available for Pro, Max, Team, or Enterprise plans and works across all platforms (macOS, Windows, Linux): 1. Open Claude Desktop. 2. Navigate to Settings > Connectors. 3. Click **Add custom connector**. 4. Enter the URL: `[https://docs.redpanda.com/mcp](https://docs.redpanda.com/mcp)` 5. The connector works straight away, on the anonymous allowance. To sign in for the higher allowance, reconnect it and complete the OAuth flow when prompted. > 📝 **NOTE** > > When using Connectors, Claude connects to your remote MCP server from Anthropic’s cloud infrastructure. **Method 2: Using Configuration File** This method works for all plans, including Free plan. Edit the Claude Desktop configuration file for your platform: - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` Add the following configuration to your `claude_desktop_config.json` file: ```json { "mcpServers": { "redpanda": { "command": "npx", "args": ["-y", "mcp-remote", "https://docs.redpanda.com/mcp"] } } } ``` This configuration uses the `mcp-remote` bridge to connect to Redpanda’s remote MCP server. On first use, `mcp-remote` opens a browser for you to sign in with your Redpanda Cloud account. Claude Desktop supports only `stdio` and `sse` transports, so `mcp-remote` converts the HTTP endpoint to a compatible format. Before you restart, sign in at [docs.redpanda.com](https://docs.redpanda.com/login) in your default browser. Claude Desktop stops `mcp-remote` when its startup timeout elapses, so a sign-in that involves creating an account cannot finish in time. See [Authentication](#authentication). Restart Claude Desktop for changes to take effect. > ❗ **IMPORTANT** > > On Linux, Claude Desktop cannot connect to remote servers configured using `claude_desktop_config.json`. If this method doesn’t work, use the Connectors interface instead (available with Pro, Max, Team, or Enterprise plans). For more details, see the [Claude Desktop documentation](https://support.anthropic.com/en/articles/9487310-desktop-app). #### [](#other-ai-tools)Other AI tools Any tool that supports the MCP OAuth flow can connect using the following URL and will prompt you to sign in with your Redpanda Cloud account on first use: ```text https://docs.redpanda.com/mcp ``` > 📝 **NOTE** > > MCP support varies by tool and version. Check the specific tool’s documentation for MCP setup instructions. See [Authentication](#authentication) for details on sign-in. #### [](#what-you-can-do)What you can do Once connected, you can ask context-aware questions about Redpanda from within your editor: - "How do I configure Redpanda for production?" - "What are the instructions for running Redpanda in a local Kind cluster?" - "What are the best practices for topic partitioning in Redpanda?" - "What are Redpanda’s security features and authentication methods?" - "How do I monitor Redpanda cluster performance?" - "What’s the difference between Redpanda Cloud and self-hosted deployment?" You can also **send feedback to the Redpanda team** through your AI client. If you hit a bug, a documentation gap, or anything unclear, tell your assistant something like "send feedback that this page is missing X" and it can submit it for us to review. If you’re signed in, we can follow up with you. #### [](#usage-limits)Usage limits To ensure fair use and performance for all users, the MCP endpoint enforces the following rate limits: - **60 requests per 15 minutes** When you’re signed in, this limit is applied per user. Unauthenticated requests (during the rollout period) are limited per IP address. As well as this limit, the `ask_redpanda_question` tool proxies to an MCP server hosted by Kapa.ai, which enforces its own limits. See the [Kapa documentation](https://docs.kapa.ai/integrations/mcp/overview#authentication) for details. These limits are suitable for: - Individual developer IDE usage - Ad-hoc documentation queries - Evaluation and testing If you exceed the limit, you receive an HTTP 429 response with rate limit headers. Wait until the reset time before retrying. Rate limit exceeded response ```text HTTP 429 Too Many Requests RateLimit-Limit: 60 RateLimit-Remaining: 0 RateLimit-Reset: ``` #### [](#troubleshooting)Troubleshooting ##### [](#authentication-required-http-401)Authentication required (HTTP 401) Anonymous access is allowed, so a `401` here means your client sent credentials the server could not accept, rather than none at all. If you receive an `HTTP 401` response with an `authentication_required` error: - Reconnect or restart the client. If sign-in succeeded before, your token may have expired, and reconnecting starts a fresh sign-in. - Check that your client supports the MCP OAuth flow (most recent versions do). A client that doesn’t can still use the server anonymously. - If you don’t have a Redpanda Cloud account, [create a free one](https://cloud.redpanda.com/sign-up?utm_source=docs&utm_medium=referral&utm_campaign=docs-signup&utm_content=how-to-use-docs). ##### [](#anonymous-tool-call-limit)Out of free tool calls for today If a tool returns an `anonymous_quota_exhausted` error, you’ve used the anonymous allowance of 10 tool calls for the day. Your agent usually reads the message out rather than showing the error, so it may reach you as a sentence about signing in. The allowance is counted per network address, so on a shared or office network you may reach it without having made 10 calls yourself. It resets 24 hours after the first call it counted. To get an allowance of your own, sign your client in. Reconnect the server, or use your client’s authenticate action for it: your client won’t prompt you on its own, because anonymous access works and nothing tells it authentication is required. See [Authentication](#authentication). ##### [](#client-sign-in-window)Sign-in opens a browser but the page fails to load If the browser ends up on a `localhost` address reporting `ERR_CONNECTION_REFUSED`, if sign-in keeps opening a new tab without ever finishing, or if the browser shows a **Finish connecting** button after you sign in, your MCP client stopped listening for the result before you finished in the browser. Clients that connect through a `stdio` bridge such as `mcp-remote` are affected: the host stops the bridge when its startup timeout elapses (30 seconds in Claude Code), and the bridge’s browser listener dies with it. The `--auth-timeout` option of `mcp-remote` does not extend this window. To get through it: - Sign in to [docs.redpanda.com](https://docs.redpanda.com/login) in your default browser first, then connect your MCP client. The client’s sign-in step is then a redirect with nothing to click, which finishes in seconds. - If the browser shows **Finish connecting**, click it within a minute. If nothing happens, reconnect the server in your client. - If you run `mcp-remote` under Claude Code, raise the startup timeout by setting `MCP_TIMEOUT=300000` in the environment Claude Code runs in, and clear any half-finished state with `rm -rf ~/.mcp-auth` before retrying. - For Claude Code, Cursor, and VS Code, use the HTTP transport shown in the setup section instead of `mcp-remote`. Those clients keep listening for as long as the session is open, so the window is not a factor. If you were creating your Redpanda Cloud account when this happened, no timeout setting is long enough to cover it: signup includes a verification email and Cloud onboarding. Finish creating the account in the browser, then reconnect your client. That sign-in is a redirect with nothing to click, because you’re already signed in to Redpanda Cloud in that browser. ##### [](#account-setup-is-not-finished)Account setup is not finished If sign-in fails with `access_denied` and a message about finishing account setup, your Redpanda Cloud account exists but does not belong to an organization yet. Verifying the address in the Cloud signup email does not create one. Complete the Redpanda Cloud onboarding steps, then reconnect your client. Retrying sign-in before onboarding is finished fails the same way every time. ##### [](#work-account-required-http-403)Work account required (HTTP 403) Any verified Redpanda Cloud account works by default, including personal email providers. If your organization has opted to restrict access to work email domains and you receive an `HTTP 403` with a `work_email_required` error, sign in with your work account instead. ##### [](#server-not-connecting)Server not connecting - Verify the URL is exactly: `[https://docs.redpanda.com/mcp](https://docs.redpanda.com/mcp)`. - Check your internet connection. - Ensure your AI tool supports HTTP-based MCP servers. - Restart your AI tool after adding the configuration. ##### [](#vs-code-specific-issues)VS Code specific issues - Ensure you have VS Code 1.102 or later. - Verify GitHub Copilot is installed and enabled. - Try running **MCP: Reset Cached Tools** from the Command Palette. - Check the Output panel (**View** > **Output** > **MCP**) for error messages. ##### [](#configuration-issues)Configuration issues - For Claude Code, Cursor, and VS Code, use the HTTP transport (`--transport http` or `"type": "http"`). - For Claude Desktop, use the `mcp-remote` bridge shown in the setup section. Claude Desktop does not support direct HTTP transport. - If you previously configured Claude Code using `mcp-remote` and experience connection issues, remove the old configuration and use the HTTP transport method shown above. - Some MCP clients may have issues with SSE streaming. If you experience connection problems, verify that your client supports HTTP-based MCP servers with Server-Sent Events (SSE). - Check that your client’s Accept headers include both `application/json` and `text/event-stream`. ##### [](#rate-limiting)Rate limiting If you’re building automation or high-volume integrations and hitting rate limits frequently: - The public endpoint’s rate limits are intentionally restrictive for fair use. - Consider implementing caching on your side to reduce duplicate queries. ##### [](#other-issues)Other issues Check the [MCP GitHub repository](https://github.com/modelcontextprotocol/servers) for additional troubleshooting guidance, or contact [Redpanda support](https://support.redpanda.com) to report a problem with our documentation. ### [](#static-markdown-exports)Static markdown exports For agents without MCP support or for offline processing, use our static markdown exports: **Component-specific exports:** - `[https://docs.redpanda.com/streaming-full.txt](https://docs.redpanda.com/streaming-full.txt)`: Redpanda Streaming documentation - `[https://docs.redpanda.com/cloud-data-platform-full.txt](https://docs.redpanda.com/cloud-data-platform-full.txt)`: Redpanda Cloud documentation - `[https://docs.redpanda.com/connect-full.txt](https://docs.redpanda.com/connect-full.txt)`: Redpanda Connect documentation - `[https://docs.redpanda.com/labs-full.txt](https://docs.redpanda.com/labs-full.txt)`: Labs and tutorials **Use cases:** - Offline AI training and model fine-tuning - Batch processing and analysis - Full-text search implementations - Custom documentation tools ### [](#fetch-individual-pages)Fetch individual pages Every HTML page in our documentation has a markdown equivalent that you can access programmatically. 1. **Direct access:** Replace `.html` with `.md` in any URL Example: `[https://docs.redpanda.com/streaming/current/get-started.html](https://docs.redpanda.com/streaming/current/get-started.html)` → `[https://docs.redpanda.com/streaming/current/get-started.md](https://docs.redpanda.com/streaming/current/get-started.md)` 2. **Content negotiation:** Request any URL with `Accept: text/markdown` header **Markdown features:** - YAML frontmatter with page metadata (title, description, categories, topic type, personas) - Git dates (accurate created/modified dates from commit history) - GitHub-Flavored Markdown format **Use cases:** - API integrations - Automated documentation pipelines - Custom documentation workflows - Integration with internal knowledge bases **Contributing:** - Found a typo or have a suggestion? Open an issue or pull request on GitHub --- # Page 3: Redpanda Documentation **URL**: https://docs.redpanda.com/home/llms.md --- # Redpanda Documentation --- title: Redpanda Documentation latest-operator-version: v26.2.4 latest-console-tag: v3.12.0 latest-connect-version: 4.113.0 latest-redpanda-tag: v26.2.4 docname: llms page-component-name: home page-version: master page-component-version: master page-component-title: Home page-relative-src-path: llms.adoc page-edit-url: https://github.com/redpanda-data/docs-site/edit/HEAD/home/modules/ROOT/pages/llms.adoc page-git-created-date: "2026-03-05" page-git-modified-date: "2026-09-10" --- > **Redpanda** is a high-performance streaming data platform and Agentic Data Plane that is fully compatible with the Apache Kafka® API. It enables real-time data streaming, event-driven architectures, and data pipelines with simple single-binary deployment and sub-millisecond latency. The Agentic Data Plane provides enterprise-grade governance and observability for AI agents, including audit trails, compliance controls, and visibility into agent behavior. Available as self-managed software or as a fully-managed cloud service. ## [](#discovery)Discovery **For AI agents and LLMs:** This documentation is optimized for AI consumption. If you’re an AI agent trying to help with Redpanda, start here. ### [](#find-redpanda-documentation)Find Redpanda documentation **Primary discovery methods:** 1. **This file**: `[https://docs.redpanda.com/llms.txt](https://docs.redpanda.com/llms.txt)` - You’re reading it! This follows the llms.txt standard and provides a curated overview with links to comprehensive resources. 2. **Sitemap**: `[https://docs.redpanda.com/sitemap.md](https://docs.redpanda.com/sitemap.md)` - Contains all documentation pages including this file and all exports. The sitemap index includes `[https://docs.redpanda.com/sitemap-llms.md](https://docs.redpanda.com/sitemap-llms.md)` with all AI-optimized exports. 3. **MCP server**: [https://docs.redpanda.com/home/how-to-use-these-docs.md](https://docs.redpanda.com/home/how-to-use-these-docs.md) - For Claude Code and MCP-compatible agents, this provides interactive documentation tools. ### [](#static-documentation-exports)Static documentation exports **For agents without MCP support**, we provide comprehensive static exports: - **[https://docs.redpanda.com/llms-full.txt](https://docs.redpanda.com/llms-full.txt)**: Every component in one file, using the latest version of each. Older versions are not included in any export; to read one, request the individual page instead (replace `.html` with `.md` in its URL). - **Component-specific exports**: Focused documentation for individual products. Smaller and cheaper to index than the full export: - **[https://docs.redpanda.com/streaming-full.txt](https://docs.redpanda.com/streaming-full.txt)**: Redpanda Streaming documentation - **[https://docs.redpanda.com/cloud-data-platform-full.txt](https://docs.redpanda.com/cloud-data-platform-full.txt)**: Redpanda Cloud documentation - **[https://docs.redpanda.com/connect-full.txt](https://docs.redpanda.com/connect-full.txt)**: Redpanda Connect documentation - **[https://docs.redpanda.com/agentic-data-plane-full.txt](https://docs.redpanda.com/agentic-data-plane-full.txt)**: Agentic Data Plane documentation - **[https://docs.redpanda.com/labs-full.txt](https://docs.redpanda.com/labs-full.txt)**: Labs and tutorials - **[https://docs.redpanda.com/home-full.txt](https://docs.redpanda.com/home-full.txt)**: Documentation home and cross-product guidance > 📝 **NOTE** > > The API reference is linked from these exports but its content is not included, because it is generated from OpenAPI specs and hosted separately. For endpoint-level detail, follow the `[https://docs.redpanda.com/api/](https://docs.redpanda.com/api/)` links. ### [](#individual-markdown-pages)Individual Markdown pages **Every HTML page has a markdown equivalent:** 1. **Direct access**: Replace `.html` with `.md` in any URL - Example: `[https://docs.redpanda.com/streaming/current/get-started.html](https://docs.redpanda.com/streaming/current/get-started.html)` → `[https://docs.redpanda.com/streaming/current/get-started.md](https://docs.redpanda.com/streaming/current/get-started.md)` 2. **Content negotiation**: Request any URL with `Accept: text/markdown` header **Markdown features:** - YAML frontmatter with page metadata (title, description, categories, topic type, personas) - Git dates (accurate created/modified dates from commit history) - GitHub-Flavored Markdown format ## [](#overview)Overview Redpanda docs serve both new and experienced users, offering detailed technical resources across Redpanda’s product suite. - **[Redpanda Streaming](https://docs.redpanda.com/streaming.md):** Deploy and manage Redpanda in your environment for ultimate control, high performance, and fault tolerance with Kafka compatibility and advanced enterprise features like Tiered Storage. - **[Redpanda Cloud](https://docs.redpanda.com/cloud-data-platform.md):** Simplify streaming with a fully-managed service: Serverless, Bring Your Own Cloud (BYOC), or Dedicated. Serverless is the fastest and easiest way to start data streaming. Choose BYOC for full data sovereignty. - **[Redpanda Connect](https://docs.redpanda.com/connect.md):** Effortlessly integrate data across systems with hundreds of prebuilt connectors, change data capture (CDC) capabilities, and YAML-configurable workflows. Available as a standalone solution or as part of Redpanda Streaming, Redpanda Connect empowers organizations to build scalable, high-performance data pipelines with minimal complexity. - **[Redpanda Agentic Data Plane](https://docs.redpanda.com/agentic-data-plane/get-started/adp-overview.md):** Enterprise-grade infrastructure for building, deploying, and governing AI agents at scale. Provides Model Context Protocol (MCP) integration, declarative agent configuration, and compliance-grade audit trails for AI agents that need direct access to databases, queues, and business systems. - **[Redpanda Console](https://docs.redpanda.com/streaming/current/console.md):** Streamline operations with an intuitive Kafka UI for managing topics, partitions, and consumer groups, providing visibility and control over your data pipeline. ## [](#core-documentation)Core documentation - [Get started](https://docs.redpanda.com/streaming/current/get-started/quickstarts.md): Fast-track your journey with Redpanda Streaming by deploying a complete example in Docker. - [Redpanda concepts](https://docs.redpanda.com/streaming/current/get-started/architecture.md): Deep-dive into key concepts like Tiered Storage, partitions, replication, and data streaming architecture. ## [](#deployment-guides)Deployment guides - [Redpanda Streaming](https://docs.redpanda.com/streaming/current/deploy.md): Install and configure Redpanda and Redpanda Console in self-hosted environments, including production best practices. Choose from Linux (bare-metal) or Kubernetes deployment instructions. - [Redpanda Cloud](https://docs.redpanda.com/cloud-data-platform/get-started/cluster-types.md): Guides for using Redpanda Cloud across Serverless, BYOC, and Dedicated options. - [Redpanda Connect](https://docs.redpanda.com/connect.md): Standalone documentation for deploying and managing Redpanda Connect, with or without Redpanda. ## [](#redpanda-cli)Redpanda CLI Learn about `rpk`, the comprehensive command-line interface tool for managing Redpanda clusters. - [rpk documentation for Redpanda Streaming](https://docs.redpanda.com/streaming/current/reference/rpk/rpk-commands.md) - [rpk documentation for Redpanda Cloud](https://docs.redpanda.com/cloud-data-platform/reference/rpk/rpk-commands.md) ## [](#redpanda-console)Redpanda Console - [About Redpanda Console](https://docs.redpanda.com/streaming/current/console.md): Learn about Redpanda’s Kafka UI for managing topics, partitions, and consumer groups. - [Configure Redpanda Console](https://docs.redpanda.com/streaming/current/manage/console.md): Learn how to configure Redpanda Console for your needs. ## [](#ai-agents-and-agentic-data-plane)AI agents and Agentic Data Plane Build and deploy production-ready AI agents with enterprise governance and compliance. ### [](#get-started)Get started - [Agentic Data Plane Overview](https://docs.redpanda.com/agentic-data-plane/get-started/adp-overview.md): Enterprise infrastructure for AI agents with built-in governance, observability, and compliance. - [Quickstart for Administrators](https://docs.redpanda.com/agentic-data-plane/get-started/adp-quickstart.md): Set up Agentic Data Plane for your organization. Configure an LLM provider, verify it, and hand off to your agent builders. - [Quickstart for Agent Builders](https://docs.redpanda.com/agentic-data-plane/get-started/agent-builder-quickstart.md): Sign in, explore the agents your organization runs, then build and test your own agent backed by MCP tools. ### [](#build-agents-and-connect-tools)Build agents and connect tools - [How Agents Work](https://docs.redpanda.com/agentic-data-plane/connect/agents-overview.md): Build agents declaratively by selecting an LLM, writing a system prompt, and attaching prebuilt tools and integrations instead of writing custom agent code. - [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. - [Plug in an App, Database, or Tool](https://docs.redpanda.com/agentic-data-plane/connect/managed/managed-catalog.md): Every managed MCP server type Redpanda hosts, grouped by category, with links to setup guides. - [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. ### [](#ai-gateway-and-llm-providers)AI Gateway and LLM providers - [How AI Gateway Works](https://docs.redpanda.com/agentic-data-plane/gateway/overview.md): The managed proxy for LLM APIs in Agentic Data Plane. Each provider gets a Redpanda-hosted URL with secrets, authentication, and observability. - [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 AI, AWS Bedrock, or any OpenAI-compatible endpoint. - [Set Up AWS Bedrock as an LLM Provider](https://docs.redpanda.com/agentic-data-plane/gateway/bedrock-setup.md): Create the IAM user, policy, and access keys AI Gateway needs to invoke Amazon Bedrock models, then register the provider. - [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 or OIDC client credentials, and send requests with your SDK. - [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, or AWS Bedrock provider. ### [](#govern-and-observe)Govern and observe - [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. - [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, with conditions over resource tags and ownership. - [Set Up Budgets](https://docs.redpanda.com/agentic-data-plane/control/budgets.md): Cap LLM spend with per-agent budgets and see what Agentic Data Plane records automatically. - [Analyze Cost and Usage](https://docs.redpanda.com/agentic-data-plane/control/cost-usage.md): Break down LLM spend, requests, and tokens by provider, model, agent, user, or tag. Compare periods and export CSV. - [Review the Audit Log](https://docs.redpanda.com/agentic-data-plane/monitor/audit-log.md): Review authorization decisions, filter them, and see who acted on which resource and whether the request was allowed. - [See What Your Agent Did](https://docs.redpanda.com/agentic-data-plane/monitor/transcripts.md): Open a transcript, read the conversation turn by turn, and investigate errors and performance. ### [](#command-line-and-gitops)Command line and GitOps - [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, and agents. - [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 for declarative create-or-update, drift detection, and CI gating. ## [](#api-references)API references - [Admin API](https://docs.redpanda.com/api/doc/admin.md): Manage and monitor Redpanda clusters using this REST API, including operations for configuration, partitions, and node health. - [Schema Registry API](https://docs.redpanda.com/api/doc/schema-registry.md): Use Redpanda’s Kafka-compatible schema registry for managing and evolving schemas in your data streams. - [HTTP Proxy API](https://docs.redpanda.com/api/doc/http-proxy.md): Simplify interactions with Kafka topics and partitions with Redpanda’s HTTP Proxy API, enabling easier data production and consumption over HTTP. - [Cloud API](https://docs.redpanda.com/api/doc/cloud-controlplane.md): Access and manage Redpanda Cloud resources programmatically, including provisioning clusters, monitoring usage, and configuring deployments. ## [](#troubleshooting)Troubleshooting - [Troubleshooting guide](https://docs.redpanda.com/streaming/current/troubleshoot.md): Resolve common issues with installation, configuration, and performance. - [Debug bundles](https://docs.redpanda.com/streaming/current/troubleshoot/debug-bundle.md): Generate and analyze debug bundles for diagnosing cluster issues. ---