Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| cdp_launch | Launch a Chrome/Chromium browser with CDP enabled. Creates a dedicated profile directory. |
| cdp_connect | Connect to an already-running Chrome/Chromium instance with CDP enabled. |
| cdp_list_tabs | List all open browser tabs. |
| cdp_navigate | Navigate to a URL or perform navigation actions (back, forward, refresh). |
| cdp_find_elements | Discover interactive elements on the page (inputs, buttons, links, etc.). |
| cdp_interact | Interact with elements: click, type, upload files, select options, etc. |
| cdp_read | Read content from the page: full page text, element text, attributes. |
| cdp_screenshot | Capture a screenshot of the page or a specific element. |
| cdp_wait | Wait for conditions: element visible, text contains, navigation, etc. |
| cdp_execute | Execute JavaScript in the page context. |
| cdp_list_frames | List all frames on the page (main frame + iframes). Use this to find iframes for LinkedIn Easy Apply, Gmail compose, etc. |
| cdp_frame_interact | Interact with elements inside iframes. Automatically searches all frames for the element. |
| cdp_type_text | Type text at the current cursor position using CDP Input.insertText. This simulates real keyboard input and works with React/Vue/Angular controlled inputs. Focus an element first with cdp_interact focus action. |
| cdp_click_coordinates | Click at raw x,y screen coordinates. Useful for clicking elements in shadow DOM or other hard-to-select elements. Get coordinates from screenshots or cdp_find_elements rect values. |
| cdp_upload_shadow | Upload a file to a file input in shadow DOM. First use cdp_execute to find the file input and store it in window.__fileInput, then call this tool. |
| cdp_set_value | Set the value of an input/textarea, properly handling React/Vue/Angular controlled inputs. This clears existing content and sets new value, triggering all necessary events. Best for form fields that cdp_interact type struggles with. |
| cdp_monaco_editor | Interact with Monaco Editor (VS Code web editor) on the page. Detects Monaco instances and provides reliable get/set operations that preserve formatting. Much better than generic text input tools for Monaco. |
| cdp_submit_form | Submit a form reliably, with special handling for React/Vue/Angular. Tries multiple submission methods: requestSubmit(), clicking submit button, dispatching submit event, and direct submit(). Works when Enter key fails. |
| cdp_site_scan | Scan current page structure and store in site memory. Detects iframes, shadow DOM, forms, and key elements. Automatically skips if already scanned this conversation epoch (compaction resets this). Use force=true to rescan anyway. |
| cdp_site_info | Get stored site memory for the current page or a specific domain. Returns iframe locations, shadow DOM elements, and interaction patterns learned from previous visits. |
| cdp_site_note | Add a note or selector pattern to site memory. Use this to record what you learned about interacting with a site. |
| cdp_site_list | List all sites in memory with their key info. |
| cdp_site_clear | Clear site memory for a domain (forces fresh scan next time). |
| cdp_epoch_info | Get current epoch info. Useful for debugging site memory behavior. |
| cdp_track_bug | Track a bug in the CDP-MCP. Writes to BUGS.md in the cdp-mcp folder. Use this when you encounter issues with browser automation. |
| cdp_list_bugs | List all tracked bugs in CDP-MCP. |
| cdp_fix_bug | Mark a bug as fixed and remove it from the tracking file. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |