Add integrations/claude section with Claude Code + Desktop page

changelog.mdx

@@ -90,15 +90,15 @@ For API library updates, see the [Node SDK](https://github.com/onkernel/kernel-n
 <Update label="June 12" tags={["Product", "Docs"]}>
 ## Product updates
 
-- Released the [Kernel × Claude Managed Agents cookbook](https://github.com/kernel/claude-managed-agents-kernel), a public recipe for running parallel computer-use agent swarms with [Claude Managed Agents](/integrations/claude-managed-agents) on Kernel cloud browsers, with API keys secured via Vaults.
+- Released the [Kernel × Claude Managed Agents cookbook](https://github.com/kernel/claude-managed-agents-kernel), a public recipe for running parallel computer-use agent swarms with [Claude Managed Agents](/integrations/claude/claude-managed-agents) on Kernel cloud browsers, with API keys secured via Vaults.
 - Shipped a `kernel-browser-harness` [skill](https://github.com/kernel/skills) for setting up Kernel browser sessions inside Claude Code with persistent session IDs across calls.
 - Extended `kernel browsers acquire` in the [CLI](https://github.com/kernel/cli) with `name` and `tags` parameters, so pooled browsers can be labeled at acquisition time alongside `browsers create`.
 - Made browser [telemetry](/browsers/telemetry) categories opt-in. The `--telemetry` flag (and `telemetry` request config) now records only the categories you list; enabling telemetry without specifying categories ships a small default set instead of every category.
 
 ## Documentation updates
 
 - Published a new [browser telemetry](/browsers/telemetry) guide covering categories, the stream API, and event shapes.
-- Wrote a [Claude Managed Agents](/integrations/claude-managed-agents) integration guide with a link to the public cookbook.
+- Wrote a [Claude Managed Agents](/integrations/claude/claude-managed-agents) integration guide with a link to the public cookbook.
 - Documented the org-wide default [per-project concurrency cap](/info/projects) on the Projects page.
 - Expanded the [CLI reference](/reference/cli) to include several previously missing subcommands.
 </Update>
@@ -438,7 +438,7 @@ For API library updates, see the [Node SDK](https://github.com/onkernel/kernel-n
 - Introduced a new [Hobbyist plan](https://www.kernel.sh/#pricing), which provides affordable access to features like session replays, uploading and downloading files, and using custom Chrome extensions.
 - Updated the Gemini [Computer Use template](/integrations/computer-use/gemini) to [use](https://github.com/kernel/cli) Stagehand V3, resolving compatibility issues.
 - Added support for Actor and Thinker [OpenAGI models](https://github.com/kernel/kernel-oagi), with guidance on when to use each approach.
-- Added new [Claude Agent SDK templates](/integrations/claude-agent-sdk) for TypeScript and Python that demonstrate browser automation using Kernel's Playwright execution API.
+- Added new [Claude Agent SDK templates](/integrations/claude/claude-agent-sdk) for TypeScript and Python that demonstrate browser automation using Kernel's Playwright execution API.
 
 ## Documentation updates
 - Added documentation for the OpenAGI Lux [integration](/integrations/computer-use/openagi) using the `kernel create` method, including examples for both `AsyncDefaultAgent` and `TaskerAgent`.

docs.json

@@ -12,6 +12,9 @@
     { "source": "/auth/agent/faq", "destination": "/auth/faq" },
     { "source": "/browsers/hardware-acceleration", "destination": "/browsers/gpu-acceleration" },
     { "source": "/integrations/computer-use", "destination": "/integrations/computer-use/overview" },
+    { "source": "/integrations/claude", "destination": "/integrations/claude/overview" },
+    { "source": "/integrations/claude-agent-sdk", "destination": "/integrations/claude/claude-agent-sdk" },
+    { "source": "/integrations/claude-managed-agents", "destination": "/integrations/claude/claude-managed-agents" },
     { "source": "/browsers/create-a-browser", "destination": "/introduction/create" },
     { "source": "/browsers/pools/scaling", "destination": "/introduction/scale" },
     { "source": "/introduction", "destination": "/" },
@@ -206,8 +209,15 @@
               "integrations/agent-browser",
               "integrations/browser-use",
               "integrations/hermes-agent",
-              "integrations/claude-agent-sdk",
-              "integrations/claude-managed-agents",
+              {
+                "group": "Claude",
+                "pages": [
+                  "integrations/claude/overview",
+                  "integrations/claude/claude-code-and-desktop",
+                  "integrations/claude/claude-agent-sdk",
+                  "integrations/claude/claude-managed-agents"
+                ]
+              },
               {
                 "group": "Computer Use",
                 "pages": [

integrations/claude/claude-code-and-desktop.mdx

@@ -0,0 +1,52 @@
+---
+title: "Claude Code and Desktop"
+description: "Give Claude Code and Claude Desktop a Kernel cloud browser"
+---
+
+Connect the Claude apps you already use to Kernel. There are two ways to bring Kernel into [Claude Code](https://www.claude.com/product/claude-code):
+
+- **Marketplace plugin** — load Kernel's skills directly into Claude Code so it knows how to manage cloud browsers and write automations.
+- **Remote MCP server** — connect Claude Code to Kernel's [MCP server](/reference/mcp-server) to create and manage cloud browsers from chat.
+
+## Marketplace plugin (Claude Code)
+
+Kernel publishes an [official skills marketplace](https://github.com/kernel/skills) for Claude Code. Installing a plugin from it loads Kernel's best-practice skills into your coding agent.
+
+Run these in the Claude Code REPL, one line at a time:
+
+```bash
+/plugin marketplace add kernel/skills
+/plugin install kernel-cli
+/plugin install kernel-sdks
+```
+
+Each plugin bundles a set of skills:
+
+- **`kernel-cli`** — managing browsers, apps, profiles, and proxies from the CLI, plus managed auth, session debugging, and bot-detection profiling.
+- **`kernel-sdks`** — building browser automation with the TypeScript and Python SDKs.
+
+See the [skills repo](https://github.com/kernel/skills#available-skills) for the current list.
+
+## Remote MCP server (Claude Code)
+
+Add Kernel's remote MCP server to manage cloud browsers from Claude Code.
+
+**Using the Kernel CLI (recommended):**
+
+```bash
+kernel mcp install --target claude-code
+# Then in the REPL run once to authenticate:
+/mcp
+```
+
+**Manual setup:**
+
+```bash
+claude mcp add --transport http kernel https://mcp.onkernel.com/mcp
+# Then in the REPL run once to authenticate:
+/mcp
+```
+
+## Claude Desktop
+
+Claude Desktop reaches Kernel through the same remote MCP server, added as a custom connector under **Settings → Connectors**. The [Claude client guide](/reference/mcp-server/clients/claude) has the steps, and covers Claude.ai as well.

integrations/claude-managed-agents.mdx → integrations/claude/claude-managed-agents.mdx

@@ -9,7 +9,7 @@ The browsers are provisioned and controlled through the [Kernel CLI](/reference/
 This integration combines Claude's hosted agent runtime with Kernel's cloud browsers. Claude Managed Agents owns the **runtime** — it runs the agent loop in an Anthropic-managed sandbox with bash, file tools, and any custom tools you declare. Kernel owns the **browser** — a fresh, isolated, stealth Chromium session per run that the agent drives to load, read, and act on real pages. Each side handles what it's best at, and you operate neither.
 
 <Note>
-This is different from the [Claude Agent SDK](/integrations/claude-agent-sdk) integration. The **Agent SDK** is a library you run on your own machine or deploy as a Kernel app. **Managed Agents** is Anthropic's *hosted* harness — agents, sessions, environments, and vaults all live on Anthropic's side, and the agent reaches Kernel over the network. Use this page when you want Anthropic to host the agent loop.
+This is different from the [Claude Agent SDK](/integrations/claude/claude-agent-sdk) integration. The **Agent SDK** is a library you run on your own machine or deploy as a Kernel app. **Managed Agents** is Anthropic's *hosted* harness — agents, sessions, environments, and vaults all live on Anthropic's side, and the agent reaches Kernel over the network. Use this page when you want Anthropic to host the agent loop.
 </Note>
 
 <Info>

integrations/claude/overview.mdx

@@ -0,0 +1,52 @@
+---
+title: "Overview"
+description: "Give Claude a Kernel cloud browser — across Claude Code, Claude Desktop, the Agent SDK, and Managed Agents"
+---
+
+## Claude + Kernel
+
+Kernel gives Claude a real, cloud-hosted browser to work in, so your agents can load pages, read rendered content, and act on the web without you running any browser infrastructure. There are a few ways to connect Claude to Kernel depending on where your agent runs:
+
+### Claude Code and Claude Desktop
+
+Connect the Claude apps you already use to Kernel. Add Kernel's [remote MCP server](/reference/mcp-server) to manage cloud browsers from Claude Code or Claude Desktop, or install the [marketplace plugin](https://github.com/kernel/skills#claude-code) to load Kernel's CLI and SDK skills into Claude Code.
+
+[Set up Claude Code and Desktop →](/integrations/claude/claude-code-and-desktop)
+
+### Claude Agent SDK
+
+The [Claude Agent SDK](https://platform.claude.com/docs/en/agent-sdk/overview) is a library you run yourself — on your own machine or deployed as a Kernel app. Pair it with Kernel's Playwright Execution API to build agents that browse the web and interact with websites on cloud browsers.
+
+[Learn more about the Claude Agent SDK →](/integrations/claude/claude-agent-sdk)
+
+### Claude Managed Agents
+
+[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) is Anthropic's hosted agent harness: define an agent once, then start as many cloud sessions as you need. Claude runs the agent loop in an Anthropic-managed sandbox; Kernel provisions a fresh, isolated Chromium session per run that the agent drives. You run neither the agent loop nor the browser.
+
+[Learn more about Claude Managed Agents →](/integrations/claude/claude-managed-agents)
+
+## Next Steps
+
+<CardGroup cols={3}>
+  <Card
+    title="Claude Code and Desktop"
+    icon="terminal"
+    href="/integrations/claude/claude-code-and-desktop"
+  >
+    Give the Claude apps a Kernel browser
+  </Card>
+  <Card
+    title="Claude Agent SDK"
+    icon="robot"
+    href="/integrations/claude/claude-agent-sdk"
+  >
+    Run Agent SDK automations on cloud browsers
+  </Card>
+  <Card
+    title="Claude Managed Agents"
+    icon="cloud"
+    href="/integrations/claude/claude-managed-agents"
+  >
+    Run Anthropic's hosted agent harness against cloud browsers
+  </Card>
+</CardGroup>

integrations/overview.mdx

@@ -30,8 +30,9 @@ Kernel provides detailed guides for popular agent frameworks:
 - **[Agent Browser](/integrations/agent-browser)** - Browser automation CLI for AI agents
 - **[Browser Use](/integrations/browser-use)** - AI browser agent framework
 - **[Hermes Agent](/integrations/hermes-agent)** - Run Hermes browser tools on Kernel cloud browsers
-- **[Claude Agent SDK](/integrations/claude-agent-sdk)** - Run Claude Agent SDK automations in cloud browsers
-- **[Claude Managed Agents](/integrations/claude-managed-agents)** - Run Anthropic's hosted agent harness against cloud browsers
+- **[Claude Code and Desktop](/integrations/claude/claude-code-and-desktop)** - Give the Claude apps a Kernel browser via the marketplace plugin or MCP
+- **[Claude Agent SDK](/integrations/claude/claude-agent-sdk)** - Run Claude Agent SDK automations in cloud browsers
+- **[Claude Managed Agents](/integrations/claude/claude-managed-agents)** - Run Anthropic's hosted agent harness against cloud browsers
 - **[Stagehand](/integrations/stagehand)** - AI browser automation with natural language
 - **[Computer Use (Anthropic)](/integrations/computer-use/anthropic)** - Claude's computer use capability
 - **[Computer Use (OpenAI)](/integrations/computer-use/openai)** - OpenAI's computer use capability