MCP Log Reader
This server allows you to read, analyze, and debug MCP logs with the following capabilities:
Read logs from standard locations across macOS, Windows, and Linux
Filter log entries using case-insensitive text searches
Paginate through large log collections efficiently
Limit processed lines to control the amount of data read from each file
Customize log directory by specifying a custom path when needed
Set file limits per page for efficient browsing
Integrate seamlessly with Claude Desktop
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Log Reader show me recent MCP errors with filter='connection' lines=20"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server: Analyze & Debug MCP Logs
🎯 Overview
MCP Log Reader is a specialized MCP server that helps you analyze and debug Model Context Protocol logs. It provides Claude with direct access to log files, making it easy to troubleshoot MCP integrations and understand how Claude interacts with your tools.
Multi-platform Support: Works on macOS, Windows, and Linux with platform-specific log paths
Smart Filtering: Find specific log entries with case-insensitive text search
Paginated Browsing: Navigate large log collections efficiently
Size Management: Handles large log files with intelligent truncation
Seamless Claude Integration: Works directly with Claude Desktop
Related MCP server: Log Analyzer MCP
🚀 Quick Start
Installing via Smithery
To install MCP Log Reader for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @klara-research/MCP-Analyzer --client claudeInstalling Manually
Install directly from GitHub:
# Clone the repository
git clone https://github.com/klara-research/MCP-Analyzer.git
cd MCP-Analyzer
# Install dependencies
npm iBuild and run:
# Compile TypeScript
npx tsc🔌 Connecting to Claude
Add the server to your Claude Desktop configuration:
{
"mcpServers": {
"log-reader": {
"command": "node",
"args": [
"/absolute/path/MCP-Analyzer/build"
]
}
}
}Then restart Claude Desktop.
📋 Available Parameters
The log reader supports these parameters:
Parameter | Description | Default |
| Number of lines to read from each log file | 100 |
| Text to filter log entries by (case-insensitive) | "" |
| Custom path to log directory | OS-specific |
| Maximum number of files to read per page | 5 |
| Page number for pagination | 1 |
💡 Example Usage
Ask Claude to use the log reader tool:
Can you check my MCP logs for any connection errors in the last day?Or with specific parameters:
Can you look through MCP logs with filter="error" and lines=50 to find initialization issues?⚙️ How It Works
The server automatically detects your OS and finds the appropriate log directory
It locates all MCP log files and sorts them by modification time (newest first)
The requested page of log files is retrieved based on pagination settings
Files are processed with size limits to prevent overwhelming responses
Filtered content is returned in a structured format with pagination details
📄 License
MIT License
Available Tools
1 toolread_mcp_logsC
Read MCP logs from the standard location
Inputs: customPath, fileLimit, filter, lines, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools, making disambiguation perfect. The tool's purpose is clearly defined as reading MCP logs from a standard location, leaving no room for confusion with other tools.
The single tool name 'read_mcp_logs' follows a clear verb_noun pattern, which is inherently consistent as there are no other tools to compare it against. This naming convention is straightforward and predictable for any potential future tools.
A single tool is too few for a server named 'MCP Log Reader', as it suggests a limited scope that may not cover common log-related operations like filtering, searching, or managing logs. This minimal count feels thin and inadequate for the apparent domain of log reading.
The tool surface is severely incomplete for log reading; it only provides a basic read function without essential operations such as filtering by date, searching for specific entries, or handling different log levels. This gap will likely cause agent failures when more complex log interactions are needed.
Maintenance
Related MCP Connectors
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for building and testing AI agents with multi-model experimentation and insights.
Shared memory MCP server for Claude Code, Codex, Gemini CLI and Cursor. Cited, editable.
Analytics and debugging for your MCP server — explore usage and sessions, then root-cause errors.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA customizable Model Context Protocol server built with mcp-framework that enables Claude to access external tools and capabilities through a standardized interface.85 npm-
- AlicenseAqualityCmaintenanceAn MCP server for AI-powered log analysis that enables parsing, searching, and debugging across nine log formats directly within Claude. It features automated error extraction, sensitive data scanning, and streaming support for large log files.1439 PyPI5MIT
- AlicenseNot gradedqualityBmaintenanceAn MCP server that connects Claude (or any MCP compatible client) to your existing log infrastructure. Query, summarize, and trace logs in plain English across GCP Cloud Logging, AWS CloudWatch, Azure Log Analytics, Grafana Loki, and Elasticsearch without writing filter expressions or leaving your editor.49 npm5MIT
- AlicenseAqualityDmaintenanceMCP server for log file analysis. Gives LLMs the ability to efficiently analyze large log files without loading them into context.7101MIT