Screenshot Server

Created By
KunihiroSa year ago
Overview

what is Screenshot Server?

Screenshot Server is a modular communication protocol (MCP) server designed to capture screenshots and provide their file paths for use by other processes or AI assistants.

how to use Screenshot Server?

To use the Screenshot Server, an MCP Host (like an AI assistant) calls the take_screenshot_and_return_path tool, which captures the screen, saves it as an image file, and returns the absolute path to that file.

key features of Screenshot Server?

  • Captures screenshots and saves them to a specified location.
  • Returns the absolute file path of the saved screenshot for further processing.
  • Supports custom save locations and filenames through the take_screenshot_path tool.

use cases of Screenshot Server?

  1. Integrating with AI assistants to capture and analyze screen content.
  2. Automating screenshot capture for documentation or reporting purposes.
  3. Facilitating image processing workflows by providing file paths to other tools.

FAQ from Screenshot Server?

  • What programming language is required to run the Screenshot Server?

Python 3.x is required to run the server.

  • How do I install the necessary dependencies?

Use the command uv sync to install required libraries like mcp[cli], pyautogui, and Pillow.

  • Can I specify where to save the screenshots?

Yes! You can use the take_screenshot_path tool to specify the directory and filename for the screenshot.

Server Config

{
  "mcpServers": {
    "Screenshot-server": {
      "command": "powershell.exe",
      "args": [
        "-Command",
        "Invoke-Command -ScriptBlock { cd '<YOUR_WINDOWS_PROJECT_PATH>'; & '<YOUR_WINDOWS_UV_PATH>' run screenshot.py }"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
KunihiroS
Star
-
Language
-
License
-

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago