// MCP TOOL REFERENCE

CHARLOTTE TOOLS

43 tools from the Charlotte MCP Server, categorised by risk level.

// ALL 43 CHARLOTTE TOOLS

READ 10 tools

Read charlotte_console Retrieve console messages from the active page. Returns messages at all severity levels (log, info, warning... Read charlotte_find Search for elements matching criteria. Filters interactive elements by text, role, type, or spatial proximi... Read charlotte_get_cookies Get cookies for the active page. Optionally filter by URL(s). Returns cookie name, value, domain, path, and... Read charlotte_observe Get current page state without performing any action. Use detail levels to control verbosity: Read charlotte_requests Retrieve network request history from the active page. Returns all HTTP requests with method, status, resou... Read charlotte_screenshot Capture a visual screenshot. Fallback for when structured representation isn Read charlotte_screenshot_delete Delete a saved screenshot artifact by its ID. Removes the file from disk. Read charlotte_screenshot_get Retrieve a previously saved screenshot artifact by its ID. Returns the image data and metadata. Read charlotte_screenshots List all saved screenshot artifacts. Returns metadata for each saved screenshot including ID, filename, pag... Read charlotte_tabs List all open browser tabs with their URLs, titles, and active status.

WRITE 26 tools

Write charlotte_back Navigate back in browser history. Returns page representation after navigation. Write charlotte_click Click an interactive element on the page. Returns full page representation after the click. Write charlotte_click_at Click at specific page coordinates. Use when target elements are not in the accessibility tree (custom widg... Write charlotte_configure Configure Charlotte runtime settings. Changes take effect immediately. Write charlotte_dev_inject Inject CSS or JavaScript into the current page for testing modifications without editing files. Returns the... Write charlotte_dialog Handle a pending JavaScript dialog (alert, confirm, prompt, beforeunload). Accept or dismiss the dialog. Re... Write charlotte_diff Compare current page state to a previous snapshot. Returns structural diff showing added, removed, moved, a... Write charlotte_drag Drag an element to another element. Uses mouse primitives to simulate drag-and-drop. Returns full page repr... Write charlotte_fill_form Fill multiple form fields in a single call. Auto-detects element types (text input, select, checkbox, etc.)... Write charlotte_forward Navigate forward in browser history. Returns page representation after navigation. Write charlotte_key Send keyboard input to the page or a specific element. Supports single key with modifiers, or a sequence of... Write charlotte_network Configure network conditions for the active page. Set throttling presets, block URL patterns, or enable req... Write charlotte_reload Reload the current page. Returns page representation after reload. Write charlotte_scroll Scroll the page or a specific container. Returns full page representation after scrolling. Write charlotte_select Select an option in a select/dropdown element. Returns full page representation after selection. Write charlotte_set_cookies Set cookies on the active page. Cookies persist for subsequent navigations within matching domains. Write charlotte_set_headers Set extra HTTP headers for subsequent requests. Headers persist for all navigations on the active page. Write charlotte_submit Submit a form. Can submit by form ID or by clicking its submit button. Returns full page representation aft... Write charlotte_tab_close Close a browser tab by its ID. If the closed tab was active, switches to the first remaining tab. Write charlotte_tab_open Open a new browser tab. Optionally navigate to a URL. The new tab becomes the active tab. Write charlotte_tab_switch Switch to a different browser tab by its tab ID. Returns the page representation of the activated tab. Write charlotte_toggle Toggle a checkbox or switch element. Returns full page representation after toggle. Write charlotte_tools Manage Charlotte tool visibility. Lists available tool groups and their Write charlotte_type Type text into an input element. Returns full page representation after typing. Write charlotte_upload Set files on a file input element. Validates that files exist and that the target is a file input. Returns ... Write charlotte_viewport Change the browser viewport dimensions. Use a device preset or specify custom width/height. Returns page re...

DESTRUCTIVE 1 tools

Destructive charlotte_clear_cookies Clear cookies from the browser. Optionally filter by name(s) to remove specific cookies. Without a filter, ...

EXECUTE 6 tools

Execute charlotte_dev_audit Run accessibility and quality audits on the current page. Returns findings with severity levels and actiona... Execute charlotte_dev_serve Serve a local directory as a static website and optionally watch for file changes. Navigates to the served ... Execute charlotte_evaluate Execute JavaScript in page context. Supports single expressions and multi-statement code. Returns the compl... Execute charlotte_hover Hover over an element to trigger hover states. Returns full page representation after hover. Execute charlotte_navigate Load a URL in the active page. Returns page representation after navigation. Default minimal detail include... Execute charlotte_wait_for Wait for a condition to be met on the page. Returns page representation when the condition is satisfied, or...

// RUNNING THIS SERVER

The managed route: connect Charlotte through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @ticktockbent/charlotte

// FAQ

How many tools does the Charlotte MCP server have? +

The Charlotte MCP server exposes 43 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Charlotte tools? +

Route the Charlotte server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Charlotte tools fall into? +

Charlotte tools are categorised as Read (10), Write (26), Destructive (1), Execute (6). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.