Kernel

Deploy and manage Kernel apps, automate browsers, and search documentation with Kernel.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

Search Docs: Fast vector search through Kernel platform documentation to find relevant information, guides, tutorials, and API references. Returns ranked documentation chunks with titles, URLs, and co
List Apps: List all apps deployed in the Kernel platform. Use this to discover available apps, check their versions, or filter by specific criteria. Helpful for understanding what apps are available b
Invoke Action: Execute a specific action within a Kernel app. This is the primary way to interact with deployed apps - use this to trigger workflows, run computations, or perform operations. The actio

What data it sees

Do you need an account

No: the server works without sign-in

Deploy and manage Kernel apps, automate browsers, and search documentation with Kernel. Securely run workflows, monitor deployments, and spin up sandboxed browser sessions, all instantly accessible through a hosted service built for AI-native automation.

How to connect

How to connect Kernel to Claude

The server address to paste into Claude settings:

https://kernel.run.tools

Open Claude (claude.ai or the desktop app).
Go to Settings → Connectors.
Click Add custom connector.
Paste the server address copied below into Remote MCP server URL and click Add.
In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Kernel to ChatGPT

The server address to paste into ChatGPT settings:

https://kernel.run.tools

Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
Open Settings → Connectors and click Create.
Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Kernel to Cursor

The server address to paste into Cursor settings:

https://kernel.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (10)

Raw names from tools/list. Only developers need these.

search_docs	Fast vector search through Kernel platform documentation to find relevant information, guides, tutorials, and API references. Returns ranked documentation chunks with titles, URLs, and content snippets. Use this tool when you need to understand how Kernel features work, troubleshoot issues, or provide accurate information about the platform capabilities.
list_apps	List all apps deployed in the Kernel platform. Use this to discover available apps, check their versions, or filter by specific criteria. Helpful for understanding what apps are available before invoking actions.
invoke_action	Execute a specific action within a Kernel app. This is the primary way to interact with deployed apps - use this to trigger workflows, run computations, or perform operations. The action will run asynchronously and you can track its progress with the returned invocation ID.
get_browser	Retrieve detailed information about a specific browser session including its current status, configuration, and metadata. Use this to check if a browser is still active, get its access URLs, or understand its current state before performing operations.
create_browser	Launch a new browser session in the Kernel platform. This creates a managed browser instance that can be used for web automation, testing, or interactive browsing. The browser runs in a secure sandbox environment and can be configured with various options like headless mode, stealth mode, and session recording.
delete_browser	Permanently terminate and clean up a browser session. This will stop the browser instance, free up resources, and remove any associated data. Use this when you no longer need a browser session or want to clean up after completing automation tasks.
get_deployment	Retrieve comprehensive information about a specific deployment including its current status, build logs, configuration, and health metrics. Use this to monitor deployment progress, troubleshoot deployment issues, or verify that an app was deployed successfully.
get_invocation	Retrieve detailed information about a specific action invocation including its execution status, output data, error messages, and runtime metrics. Use this to check if an invoked action completed successfully, get its results, or troubleshoot failed executions.
list_browsers	Retrieve a list of all currently active browser sessions in the Kernel platform. This shows you which browsers are running, their session IDs, creation times, and basic configuration. Use this to discover existing browser sessions before creating new ones or to audit current browser usage.
list_deployments	Retrieve a comprehensive list of all deployments in the Kernel platform, with optional filtering by app name. This provides an overview of deployment history, current status, and allows you to track the deployment lifecycle of your apps. Use this to monitor deployment activity or find specific deployments.