Loading connector details…
Charlotte Web MCP Server
MCPOfficialOpen SourceMIT63.0
by TickTockBent • Uncategorized
An MCP server providing AI agents with structured, token-efficient access to web pages.
Example Use Cases
- 1
Efficient, token-minimized web page navigation and orientation.
- 2
Detailed, structured access to interactive elements and forms on web pages.
- 3
Development and auditing tools integrated with web browsing capabilities.
Description
Charlotte is a headless Chromium-based MCP server that decomposes web pages into structured, typed representations, enabling AI agents to receive only the necessary information at three detail levels. This approach drastically reduces token usage compared to traditional MCP servers by returning minimal page summaries on navigation and detailed data only on request, saving costs and improving efficiency. It supports navigation, observation, interaction, session management, development tools, and utilities, making it versatile for various web automation and analysis tasks.
Capabilities(16 total)
Tools (16)
charlotte_navigate
Load a URL in the active page. Returns page representation after navigation. Default minimal detail includes landmarks, headings, and interactive element counts — use charlotte_find to locate specific elements, or pass detail: 'summary' to get the full element list.
url:string*wait_for:stringtimeout:numberdetail:string
charlotte_history
Navigate browser history or reload. Returns page representation after the action.
action:string*hard:booleandetail:string
charlotte_observe
Get current page state without performing any action. Use detail levels to control verbosity: "minimal" for landmarks, headings, and interactive element counts by landmark (use charlotte_find to get specific elements with actionable IDs, or observe({ detail: "summary" }) to see all elements), "summary" (default) for content summaries and full element list, "full" for all text content. Use view: "tree" for a compact structural outline (cheapest orientation tool), or view: "tree-labeled" to include labels on interactive elements (still much cheaper than minimal JSON, and shows which button/link/input is which).
detail:stringview:stringselector:stringinclude_styles:booleanoutput_file:string
charlotte_find
Search for elements matching criteria. Filters interactive elements by text, role, type, or spatial proximity. Use the selector parameter to find DOM elements by CSS selector — this reaches elements not in the accessibility tree (custom widgets, non-semantic divs). Selector results return Charlotte element IDs usable with click, hover, drag, etc.
text:stringrole:stringtype:stringnear:stringwithin:stringselector:string
charlotte_screenshot
Capture a visual screenshot. Fallback for when structured representation isn't sufficient (complex visualizations, canvas elements, images). Use save: true to persist as a file artifact that can be referenced later.
selector:stringformat:stringquality:numbersave:booleanoutput_file:string
Quick Actions
Security
Scanned 1 month(s) agoRisk Level
MINIMAL
Read-only data retrieval, no side effects
Trust Score
B68/100
13/17 checks passed
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.
Quick Stats
Service TypeMCP
Pricing ModelFree
Capabilities16 Tools / 0 Prompts / 0 Resources
OwnerTickTockBent
CategoryUncategorized
DependenciesStandalone
Tags
ai-agentsmcpmcp-servermodel-context-protocoltypescriptweb-browsingweb-scraping