diff --git a/src/content/open-source/usage.mdx b/src/content/open-source/usage.mdx
index 237dcde..04359fc 100644
--- a/src/content/open-source/usage.mdx
+++ b/src/content/open-source/usage.mdx
@@ -7,7 +7,7 @@ description: You can dump an URL manually or start a CDP server.
 
 Use `./lightpanda help` for all options.
 
-## Dump an URL
+## Fetch a webpage
 
 ```sh copy
 ./lightpanda fetch --obey-robots --dump html https://demo-browser.lightpanda.io/campfire-commerce/
@@ -38,17 +38,98 @@ INFO  http : request complete . . . . . . . . . . . . . . . . [+234ms]
 
 ### Options
 
-The fetch command accepts options:
-* `--dump html` Dumps document to stdout in HTML. You can use also `--dump markdown` to get a Markdown version.
-* `--with-base` Add a `<base>` tag in dump
-* `--log-level` change the log level, default is `info`. `--log-level debug`.
-* `--http-proxy` The HTTP proxy to use for all HTTP requests. A username:password can be included for basic authentication. `--http-proxy http://user:password@127.0.0.1:3000`.
-* `--http-timeout` The maximum time, in milliseconds, the transfer is allowedto complete. 0 means it never times out. Defaults to `10000`.
-* `--obey-robots` Fetches and obeys the robots.txt (if available) of the web pages we make requests towards.
+### `fetch` command options
+
+```bash
+--dump          Dumps document to stdout.
+                Argument must be 'html', 'markdown', 'semantic_tree', or 'semantic_tree_text'.
+                Defaults to no dump.
+
+--strip-mode    Comma separated list of tag groups to remove from dump
+                the dump. e.g. --strip-mode js,css
+                  - "js" script and link[as=script, rel=preload]
+                  - "ui" includes img, picture, video, css and svg
+                  - "css" includes style and link[rel=stylesheet]
+                  - "full" includes js, ui and css
+
+--with-base     Add a <base> tag in dump. Defaults to false.
+
+--with-frames   Includes the contents of iframes. Defaults to false.
+
+--wait-ms       Wait time in milliseconds.
+                Defaults to 5000.
+
+--wait-until    Wait until the specified event.
+                Supported events: load, domcontentloaded, networkidle, done.
+                Defaults to 'done'.
+
+--insecure-disable-tls-host-verification
+                Disables host verification on all HTTP requests. This is an
+                advanced option which should only be set if you understand
+                and accept the risk of disabling host verification.
+
+--obey-robots
+                Fetches and obeys the robots.txt (if available) of the web pages
+                we make requests towards.
+                Defaults to false.
+
+--http-proxy    The HTTP proxy to use for all HTTP requests.
+                A username:password can be included for basic authentication.
+                Defaults to none.
+
+--proxy-bearer-token
+                The <token> to send for bearer authentication with the proxy
+                Proxy-Authorization: Bearer <token>
+
+--http-max-concurrent
+                The maximum number of concurrent HTTP requests.
+                Defaults to 10.
+
+--http-max-host-open
+                The maximum number of open connection to a given host:port.
+                Defaults to 4.
+
+--http-connect-timeout
+                The time, in milliseconds, for establishing an HTTP connection
+                before timing out. 0 means it never times out.
+                Defaults to 0.
+
+--http-timeout
+                The maximum time, in milliseconds, the transfer is allowed
+                to complete. 0 means it never times out.
+                Defaults to 10000.
+
+--http-max-response-size
+                Limits the acceptable response size for any request
+                (e.g. XHR, fetch, script loading, ...).
+                Defaults to no limit.
+
+--log-level     The log level: debug, info, warn, error or fatal.
+                Defaults towarn.
+
+--log-format    The log format: pretty or logfmt.
+                Defaults to logfmt.
+
+--log-filter-scopes
+                Filter out too verbose logs per scope:
+                http, unknown_prop, event, ...
+
+--user-agent-suffix
+                Suffix to append to the Lightpanda/X.Y User-Agent
+
+--web-bot-auth-key-file
+                Path to the Ed25519 private key PEM file.
+
+--web-bot-auth-keyid
+                The JWK thumbprint of your public key.
+
+--web-bot-auth-domain
+                Your domain e.g. yourdomain.com
+```
 
 See also [how to configure proxy](/open-source/guides/configure-a-proxy).
 
-## Start a CDP server
+## CDP server
 
 To control Lightpanda with [Chrome Devtool Protocol](https://chromedevtools.github.io/devtools-protocol/) (CDP) clients like [Playwright](https://playwright.dev/) or [Puppeteer](https://pptr.dev/), you
 need to start the browser as a CDP server.
@@ -60,22 +141,100 @@ need to start the browser as a CDP server.
 INFO  app : server running . . . . . . . . . . . . . . . . .  [+0ms]
       address = 127.0.0.1:9222
 ```
-### Options
+### `serve` command options
+
+```bash
+--host          Host of the CDP server
+                Defaults to "127.0.0.1"
+
+--port          Port of the CDP server
+                Defaults to 9222
+
+--advertise-host
+                The host to advertise, e.g. in the /json/version response.
+                Useful, for example, when --host is 0.0.0.0.
+                Defaults to --host value
+
+--timeout       Inactivity timeout in seconds before disconnecting clients
+                Defaults to 10 (seconds). Limited to 604800 (1 week).
+
+--cdp-max-connections
+                Maximum number of simultaneous CDP connections.
+                Defaults to 16.
+
+--cdp-max-pending-connections
+                Maximum pending connections in the accept queue.
+                Defaults to 128.
+
+--insecure-disable-tls-host-verification
+                Disables host verification on all HTTP requests. This is an
+                advanced option which should only be set if you understand
+                and accept the risk of disabling host verification.
+
+--obey-robots
+                Fetches and obeys the robots.txt (if available) of the web pages
+                we make requests towards.
+                Defaults to false.
+
+--http-proxy    The HTTP proxy to use for all HTTP requests.
+                A username:password can be included for basic authentication.
+                Defaults to none.
+
+--proxy-bearer-token
+                The <token> to send for bearer authentication with the proxy
+                Proxy-Authorization: Bearer <token>
+
+--http-max-concurrent
+                The maximum number of concurrent HTTP requests.
+                Defaults to 10.
+
+--http-max-host-open
+                The maximum number of open connection to a given host:port.
+                Defaults to 4.
+
+--http-connect-timeout
+                The time, in milliseconds, for establishing an HTTP connection
+                before timing out. 0 means it never times out.
+                Defaults to 0.
+
+--http-timeout
+                The maximum time, in milliseconds, the transfer is allowed
+                to complete. 0 means it never times out.
+                Defaults to 10000.
+
+--http-max-response-size
+                Limits the acceptable response size for any request
+                (e.g. XHR, fetch, script loading, ...).
+                Defaults to no limit.
+
+--log-level     The log level: debug, info, warn, error or fatal.
+                Defaults towarn.
 
-The fetch command accepts options:
-* `--host` Host of the CDP server, default `127.0.0.1`.
-* `--port` Port of the CDP server, default `9222`.
-* `--timeout` Inactivity timeout in seconds before disconnecting clients. Default `10` seconds.
-* `--log-level` change the log level, default is `info`. `--log-level debug`.
-* `--http-proxy` The HTTP proxy to use for all HTTP requests. A username:password can be included for basic authentication. `--http-proxy http://user:password@127.0.0.1:3000`.
-* `--http-timeout` The maximum time, in milliseconds, the transfer is allowedto complete. 0 means it never times out. Defaults to `10000`.
-* `--obey-robots` Fetches and obeys the robots.txt (if available) of the web pages we make requests towards.
+--log-format    The log format: pretty or logfmt.
+                Defaults to logfmt.
+
+--log-filter-scopes
+                Filter out too verbose logs per scope:
+                http, unknown_prop, event, ...
+
+--user-agent-suffix
+                Suffix to append to the Lightpanda/X.Y User-Agent
+
+--web-bot-auth-key-file
+                Path to the Ed25519 private key PEM file.
+
+--web-bot-auth-keyid
+                The JWK thumbprint of your public key.
+
+--web-bot-auth-domain
+                Your domain e.g. yourdomain.com
+```
 
 See also [how to configure proxy](/open-source/guides/configure-a-proxy).
 
 ### Connect with Puppeteer
 
-Once the CDP server started, you can run a [Puppeteer](https://pptr.dev/)
+Once the CDP server started, you can run a [Puppeteer](https://playwright.dev/)
 script by configuring the `browserWSEndpoint`.
 
 ```js copy
@@ -169,3 +328,115 @@ func main() {
     log.Println("Got title of:", title)
 }
 ```
+
+## MCP server
+
+Starts an MCP (Model Context Protocol) server over stdio
+
+
+```sh copy
+./lightpanda mcp
+```
+
+### Tools
+
+| Name | Description |
+|-|-|
+| goto | Navigate to a specified URL and load the page in memory so it can be reused later for info extraction |
+| markdown | Get the page content in markdown format. If a url is provided, it navigates to that url first. |
+| links | Extract all links in the opened page. If a url is provided, it navigates to that url first. |
+| evaluate | Evaluate JavaScript in the current page context. If a url is provided, it navigates to that url first. |
+| semantic_tree | Get the page content as a simplified semantic DOM tree for AI reasoning. If a url is provided, it navigates to that url first. |
+| interactiveElements | Extract interactive elements from the opened page. If a url is provided, it navigates to that url first. |
+| structuredData | Extract structured data (like JSON-LD, OpenGraph, etc) from the opened page. If a url is provided, it navigates to that url first. |
+| detectForms | Detect all forms on the page and return their structure including fields, types, and required status. If a url is provided, it navigates to that url first. |
+| click | Click on an interactive element. Returns the current page URL and title after the click. |
+| fill | Fill text into an input element. Returns the filled value and current page URL and title. |
+| scroll | Scroll the page or a specific element. Returns the scroll position and current page URL and title. |
+| waitForSelector | Wait for an element matching a CSS selector to appear in the page. Returns the backend node ID of the matched element. |
+
+### Options
+
+```bash
+--insecure-disable-tls-host-verification
+                Disables host verification on all HTTP requests. This is an
+                advanced option which should only be set if you understand
+                and accept the risk of disabling host verification.
+
+--obey-robots
+                Fetches and obeys the robots.txt (if available) of the web pages
+                we make requests towards.
+                Defaults to false.
+
+--http-proxy    The HTTP proxy to use for all HTTP requests.
+                A username:password can be included for basic authentication.
+                Defaults to none.
+
+--proxy-bearer-token
+                The <token> to send for bearer authentication with the proxy
+                Proxy-Authorization: Bearer <token>
+
+--http-max-concurrent
+                The maximum number of concurrent HTTP requests.
+                Defaults to 10.
+
+--http-max-host-open
+                The maximum number of open connection to a given host:port.
+                Defaults to 4.
+
+--http-connect-timeout
+                The time, in milliseconds, for establishing an HTTP connection
+                before timing out. 0 means it never times out.
+                Defaults to 0.
+
+--http-timeout
+                The maximum time, in milliseconds, the transfer is allowed
+                to complete. 0 means it never times out.
+                Defaults to 10000.
+
+--http-max-response-size
+                Limits the acceptable response size for any request
+                (e.g. XHR, fetch, script loading, ...).
+                Defaults to no limit.
+
+--log-level     The log level: debug, info, warn, error or fatal.
+                Defaults towarn.
+
+--log-format    The log format: pretty or logfmt.
+                Defaults to logfmt.
+
+--log-filter-scopes
+                Filter out too verbose logs per scope:
+                http, unknown_prop, event, ...
+
+--user-agent-suffix
+                Suffix to append to the Lightpanda/X.Y User-Agent
+
+--web-bot-auth-key-file
+                Path to the Ed25519 private key PEM file.
+
+--web-bot-auth-keyid
+                The JWK thumbprint of your public key.
+
+--web-bot-auth-domain
+                Your domain e.g. yourdomain.com
+```
+
+### Claude Desktop / Cursor / Windsurf
+
+Add to your MCP host configuration:
+
+- **Claude Desktop:** Settings > Developer > Edit Config
+- **Cursor:** `.cursor/mcp.json` in your project
+- **Windsurf:** Cascade MCP settings
+
+```json copy
+{
+  "mcpServers": {
+    "lightpanda": {
+      "command": "/path/to/lightpanda",
+      "args": ["mcp"]
+    }
+  }
+}
+```