Cursor MCP Monitor

Created By
willibrandona year ago
Real-time monitoring tool for Model Context Protocol (MCP) interactions in Cursor AI editor. Track, analyze, and debug AI context exchanges between LLM clients and servers. Supports log rotation, pattern matching, and color-coded event visualization.
Overview

What is Cursor MCP Monitor?

Cursor MCP Monitor is a real-time monitoring tool designed for tracking Model Context Protocol (MCP) interactions within the Cursor AI editor. It enables developers to analyze and debug AI context exchanges between LLM clients and servers.

How to use Cursor MCP Monitor?

To use the tool, install it globally via the .NET CLI and run it from the command line. You can monitor log files in real-time and access an interactive web-based dashboard for analysis.

Key features of Cursor MCP Monitor?

  • Real-time monitoring of MCP client-server interactions.
  • Color-coded event visualization for easy identification of message types.
  • Supports log rotation and file truncation.
  • Cross-platform compatibility (Windows, macOS, Linux).
  • Interactive dashboard for monitoring and analysis.
  • Command-line interface for customization and configuration.

Use cases of Cursor MCP Monitor?

  1. Debugging MCP server implementations by monitoring client-server interactions.
  2. Analyzing protocol messages and error patterns.
  3. Tracking client lifecycle and connection states.
  4. Monitoring server capabilities and offerings.
  5. Verifying correct protocol implementation.

FAQ from Cursor MCP Monitor?

  • Can I run Cursor MCP Monitor on different operating systems?

Yes! It supports Windows, macOS, and Linux.

  • How do I install Cursor MCP Monitor?

You can install it using the .NET CLI with the command: dotnet tool install --global CursorMCPMonitor.

  • Is there a web interface for monitoring?

Yes! The application includes a web-based dashboard accessible at http://localhost:5050.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
willibrandon
Star
6
Language
C#
License
MIT license
Category
monitoring

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