TokenScope: Token-Aware Directory Explorer

Created By
cdgaetea year ago
A tool to analyze directory structures while being mindful of token limitations for LLMs. Customize ignore files like gitignore patterns, such as .venv or node_modules
Overview

TokenScope helps LLMs like Claude efficiently explore and understand codebases by providing token-optimized directory structure analysis and content extraction. Key features include:

  • Token-aware directory scanning with configurable depth and intelligent summaries
  • File content analysis with smart token limitations and special handling for formats like JSON
  • Token usage statistics to estimate processing requirements
  • Comprehensive reporting with directory structure, token statistics, and important file samples
  • Security features restricting operations to a specified base directory

TokenScope is built with FastMCP and uses tiktoken for accurate token counting. It requires Python 3.10+ and can be installed via PyPI or directly from GitHub for development.

Server Config

{
  "mcpServers": {
    "TokenScope": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "tokenscope",
        "tokenscope",
        "--base-path",
        "/your/secure/base/path"
      ]
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
cdgaete
Star
-
Language
-
License
-
Category

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