Kernel Official

Frequently asked questions

What does the Kernel MCP server do?

Kernel MCP Server A Model Context Protocol (MCP) server that provides AI assistants with secure access to Kernel platform tools and browser automation capabilities. 🌐 Use instantly at — no installation required! What is this? The Kernel MCP Server bridges AI assistants (like Claude, Cursor, fx, or other MCP-compatible tools) with the Kernel platform, enabling them to: 🚀 Deploy and manage Kernel apps in the cloud 🌐 Launch and control headless Chromium sessions for web automation 📊 Monitor deployments and track invocations 🔍 Search Kernel documentation and inject context 💻 Execute arbitrary Playwright code against live browsers 🧠 Run persistent JavaScript Browser REPL cells with native helpers, Patchright, Playwright, and raw CDP 🎥 Record MP4 video replays of browser automation Open-source & fully-managed — the complete codebase is available here, and we run the production instance so you don't need to deploy anything. The server uses OAuth 2.0 authentication via Clerk to ensure secure access to your Kernel resources. During authorization, users can grant organization-wide access or restrict the resulting access and refresh tokens to one Kernel project. Project-scoped tokens cannot switch projects; organization-wide authorization remains available for existing workflows. For a deeper dive into why and how we built this server, see our blog post: Introducing Kernel MCP Server. Setup Instructions General (Transports) Streamable HTTP (recommended): stdio via mcp-remote (for clients without remote MCP support): npx -y mcp-remote Use the streamable HTTP endpoint where supported for increased reliability. If your client does not support remote MCP, use mcp-remote over stdio. Kernel's server is a centrally hosted, authenticated remote MCP using OAuth 2.1 with dynamic client registration. Protocol compatibility The same /mcp endpoint serves SDK v1 / 2025-era Streamable HTTP clients and protocol revision 2026-07-28 clients through the SDK v2 stateless handler. Legacy clients still initialize normally. Modern clients use per-request metadata and do not initialize or receive an MCP session ID. Both use the same tools and authentication checks; MCP Apps capabilities are read per request for modern clients. Legacy clients should handle both JSON-RPC errors and isError tool results. Unknown tools now produce JSON-RPC error -32602 ; ordinary tool failures still return isError . Validation-error text and generated tool schemas can differ from SDK v1. No byte-preserving compatibility layer or Tasks extension is installed. Run bun test 'src/app/[transport]/dual-era.test.ts' to exercise both SDK client generations over HTTP, including OAuth authorization and refresh with local upstream service fixtures. The v1 SDK is retained only as a test dependency. Quick Setup with Kernel CLI The fastest way to configure the MCP server is using the Kernel CLI: Supported Targets Target Command -------------- ----------------------------------------- Cursor kernel mcp install --target cursor Claude Desktop kernel mcp install --target claude Claude Code kernel mcp install --target claude-code VS Code kernel mcp install --target vscode Windsurf kernel mcp install --target windsurf Zed kernel mcp install --target zed Goose kernel mcp install --target goose fx kernel mcp install --target fx The CLI automatically locates your tool's config file and adds the Kernel MCP server configuration. Connect in your client Claude > Our remote MCP server is not compatible with the method Free users of Claude use to add MCP servers. Pro, Max, Team & Enterprise (Claude.ai and Claude Desktop) Go to Settings → Connectors → Add custom connector . Enter: Integration name: Kernel , Integration URL: then click Add . In Settings → Connectors , click Connect next to Kernel to launch OAuth and approve. In chat, click Search and tools and enable the Kernel tools if needed. > On Claude for Work (Team/Enterprise), only Primary Owners or Owners can enable custom connectors for the org. After it's configured, each user still needs to go to Settings → Connectors and click Connect to authorize it for their account. Claude Code CLI Cursor Automatic setup Manual setup Press ⌘/Ctrl Shift J . Go to MCP & Integrations → New MCP server . Add this configuration: Save. The server will appear in Tools. OpenCode Add the following to your /.config/opencode/opencode.jsonc : Then authenticate using the OpenCode CLI: fx Configure Kernel with the Kernel CLI: Or add Kernel to the mcp map in /.fx/mcp.json manually: Start fx, or reload the configuration in an existing session: Then authenticate with Kernel: Authorize access in the browser window that opens. Run /mcp list to verify that Kernel is connected. Goose Click here to install Kernel on Goose in one click. Goose Desktop Click Extensions in the sidebar of the Goose Desktop. Click Add custom extension . On the Add custom extension modal, enter: Extension Name : Kernel Type : STDIO Description : Access Kernel's cloud-based browsers via MCP Command : npx -y mcp-remote Timeout : 300 Click Save Changes button. Goose CLI Run the following command: Select Add Extension from the menu. Choose Command-line Extension . Follow the prompts: Extension name : Kernel Command : npx -y mcp-remote Timeout : 300 Description : Access Kernel's cloud-based browsers via MCP Visual Studio Code Press ⌘/Ctrl P → search MCP: Add Server . Select HTTP (HTTP or Server-Sent Events) . Enter: Name the server Kernel → Enter. Windsurf Press ⌘/Ctrl , to open settings. Navigate Cascade → MCP servers → View raw config . Paste: On Manage MCPs , click Refresh to load Kernel MCP. Zed Press ⌘/Ctrl , to open settings. Paste: Smithery You can connect directly to or use Smithery as a proxy using its provided URL. Use Smithery URL in any MCP client: Open Smithery: Kernel. Copy the URL from "Get connection URL". Paste it into your MCP client's "Add server" flow. Use Kernel in Smithery's Playground MCP client: Open Smithery Playground. Click "Add servers", search for "Kernel", and add it. Sign in and authorize Kernel when prompted. Others Many other MCP-capable tools accept: Command: npx Arguments: -y mcp-remote Configure these values wherever the tool expects MCP server settings. Tools Each Kernel feature has a single manage tool with an action parameter, keeping the tool set small and consistent. Standalone tools handle high-frequency and interactive workflows. One additional Managed Auth helper ( begin auth login ) is marked app-only ( meta.ui.visibility: ["app"] ); it refuses to execute on hosts that do not declare MCP Apps support. The App forwards the server-issued signed flow checkpoint to the shared manage auth connections wait action, so flow identity and terminal-state decisions stay on the server. Self-hosted deployments can select tool families with KERNEL MCP ENABLED TOOLSETS or hide them with KERNEL MCP DISABLED TOOLSETS . Both accept comma- or space-separated toolset names and standalone aliases. For example, KERNEL MCP ENABLED TOOLSETS="playwright repl computer" exposes browser-control tools without browser lifecycle or managed-auth tools, while KERNEL MCP DISABLED TOOLSETS=api keys only removes manage api keys . get connection context remains available in either mode. Call get connection context before deciding whether to create or select a project. Its canonical connection scope reports whether the connection is organization-wide or fixed to a project. Project-scoped tools advertise an optional project (name or ID) and a deprecated project id : organization-wide connections may omit them to preserve organization-wide reads and API default-project behavior, while fixed-project connections may omit them or pass the matching project. Project resources use project-qualified kernel://orgs/{organizationId}/projects/{projectId}/... URIs. Authorization remains enforced by the Kernel API; selecting a project never grants access to it. Inputs that mirror the API's nested proxy , network , browser , and proxy config objects replace older flat inputs such as proxy id , proxy routes , browser region , and custom host . The flat inputs remain as deprecated aliases, and combining one with its nested replacement is rejected. Tool-call analytics records the names, never the values, of deprecated inputs each call used in $mcp deprecated params ; the tracked list lives in src/lib/mcp/deprecated-params.ts . manage\ \ tools manage browsers - Create, update, list, get, and delete browser sessions, and read archived telemetry for active or deleted sessions. Supports headless mode, site-compatibility settings, profiles, proxies ( proxy by id, name, or mode), create-only per-host proxy routes ( network.proxy routes ) and private-host routing ( network.private hosts ), viewports, extensions, names and tags, and SSH tunneling. The browser tools ( manage browsers , computer action , execute playwright code , browser repl , exec command , browser curl , manage browser files , manage replays , webmcp ) accept a live session's name in place of its session id ; deleted sessions, and manage browser pools release, take the ID only. manage profiles - Setup (with guided live browser session), search/list with pagination, get, and delete browser profiles for persisting cookies and logins. manage projects - Create, list, get, update, and delete organization projects. Inspect and update per-project resource limits. manage api keys - Create, list, get, update, and delete org-wide or project-scoped API keys. Create returns the plaintext key once. manage browser pools - Create, list, get, delete, and flush pools of pre-warmed browsers. Acquire and release browsers from pools. manage browser files - Read, write, upload, download, and manage files in running browser VMs. Supports text and base64 input and returns binary downloads as embedded MCP resources. Paths must be absolute. read , download , and download dir zip refuse files or archives over max bytes (default 10 MiB, maximum 25 MiB) instead of truncating them; mutating actions are never retried. manage config registry - Look up current browser and proxy recommendations, start and inspect analyses, request cancellation, and list project configurations or analysis history. manage proxies - Create, list, get, check, and delete proxy configurations (datacenter, ISP, residential, mobile, custom). List filters by exact name or a query substring. manage replays - Start, stop, and list MP4 video replay recordings for a browser session. Session-scoped: start once, run your automation, then stop. Requires a paid Kernel plan. manage playwright executors - List and delete the Playwright executors of a browser session. list returns every executor ( default first) with busy , created at , last used at , and for named executors the target id and url of the tab it owns. delete takes name and an optional close tab (default true); deleting default restarts it instead of removing it. A browser can have at most 8 named executors. web search - Search the web, retrieve retained results, and inspect provider capabilities. Tool visibility uses a per-credential, per-connection Search entitlement snapshot cached for up to 30 minutes; the Search API remains authoritative for execution access. Search creation is billable and is not automatically retried. manage extensions - List and delete uploaded browser extensions. manage apps - List/search apps, invoke actions, get/list/delete deployments, and get invocation results. manage auth connections - Create, list, get, update, delete, login, submit, inspect timelines, and wait for managed-auth connections in every client. Supports health-check and automatic re-auth settings, managed-auth browser configuration, and canonical interaction-bound field/choice submissions. Use domain-filtered list for discovery. App-capable clients additionally receive open auth login ; the programmatic actions remain available there too. manage credentials - Create, list, get, update, and delete stored credentials; fetch a current TOTP code for credentials with a configured totp secret. manage credential providers - Create, list, get, update, and delete external credential providers (e.g. 1Password); list available items and test the provider connection. manage vault provider configs - Create, list, get, rename, rotate secrets, and delete organization-owned Link and AgentCard configurations. Writes require organization scope. manage vaults - Create, list, get, and delete project-owned vaults; use one per end user. manage vault wallets - Connect Kernel-hosted card wallets or Kernel-managed/configured Link/AgentCard wallets, import Link grants from a trusted backend, and inspect live payment methods and eligibility. manage vault cards - Create card requests or update supported providers according to the API's lifecycle rules; explicitly authorize an advertised Kernel card after user approval (Visa returns a hosted spend-approval action), or a Link card at the final checkout page with browser id and page url . Creating or updating a card never authorizes it. AgentCard checkout origin is caller-declared for eligible autopilot rule matching on non-prepared checkout authorizations; Kernel forwards it without comparing it with the browser page. Omission keeps the existing approval flow, autopilot may fall back to user approval, and prepared checkout uses preparation.merchant origin . It does not enable autopilot or ensure payment success. manage vault credentials - Create credentials through one of two user-chosen paths: Kernel-hosted collection (definitions for private human collection; update values or description with version and optional immutable item identity preconditions) or 1Password brokered approval (connect a 1Password account, then create a request for 1-5 logins the user approves in the 1Password app). Agents reuse an existing credential for the site first, otherwise ask the user where their login lives before creating credentials. manage vault items - List, get, invoke advertised operations (including fill and webmcp invoke with value-free bindings), observe events, and delete vault items. Read credential definitions, presence, version, collection links, and explicitly non-sensitive values; sensitive values remain hidden. collect reopens the full form; provider approvals remain user actions. Ready is not login or payment success. Kernel cards also advertise confirm transaction to report an observed merchant outcome once, and may advertise restart verification for proven no-dispatch attestation recovery only. See Vault payments for the provider flows, safety rules, and response shapes. manage browsers accepts creation-only vaults references (max 20); existing sessions and pools cannot gain vault bindings. The six vault tools share the vaults toolset and prepare/observe credentials rather than submitting merchant payments. They are exposed only when GET /org/entitlements reports features.vaults.enabled: true for the current credential; missing or unavailable entitlements hide them. Toolset configuration cannot override this access check. Credential create → collect → readiness → fill is supported entirely through MCP tools. prepare checkout remains API/CLI-only. The SDK dependency is pinned in bun.lock . For Kernel-managed Visa cards: enroll through the cardholder's private card enrollment URL, observe a connected wallet and eligible payment method, then create a card request with merchant country . After user approval, use either manage vault cards authorize or the equivalent manage vault items invoke authorize ; deliver the returned spend approval URL privately to the cardholder. Once ready, fill in a browser created with the vault attached, using the exact current HTTPS top-level page url on the merchant origin. Kernel fill supports number , expiration ( format: "MM/YY" or "MM/YYYY" ), cvc , exp month , and exp year : no billing details are stored, and billing fields fail with 400 field unavailable before any write. Enter billing name/ZIP on the merchant page. After the user submits checkout and the merchant outcome is obse

How do I install Kernel?

Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.

Is Kernel free to use?

The MCP server itself is free to install. The source is public on https://github.com/onkernel/kernel-mcp-server. Any third-party service it calls may require its own API key and account.

Which clients support Kernel?

Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.