Sentrux
Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
What is Sentrux?
Sentrux is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to real-time architectural sensor that helps ai agents close the feedback loop, enabling recursive self-improvement of code quality. pure rust.
Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Real-time architectural sensor that helps AI agents close th
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx sentruxConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Sentrux
Sentrux is a real-time architectural analysis tool written in pure Rust that monitors codebases across 52 programming languages and exposes its findings through an MCP interface. It calculates a composite quality score (0–10,000) based on modularity, acyclicity, dependency depth, equality, and redundancy, and provides 9 MCP-accessible tools that AI agents can use to scan projects, detect architectural degradation, find test gaps, and recursively improve code quality. It is designed for teams that want AI agents to have live architectural feedback during code generation and review sessions.
Prerequisites
- Rust toolchain installed (for building from source) or use the provided binary installer
- Homebrew installed on macOS (for the brew install method)
- An MCP client such as Claude Desktop or Claude Code
- A code project directory for Sentrux to analyze
Install Sentrux
Choose the installation method for your operating system.
# macOS:
brew install sentrux/tap/sentrux
# Linux:
curl -fsSL https://raw.githubusercontent.com/sentrux/sentrux/main/install.sh | sh
# Windows:
curl -L -o sentrux.exe https://github.com/sentrux/sentrux/releases/latest/download/sentrux-windows-x86_64.exe
# From source:
git clone https://github.com/sentrux/sentrux.git && cd sentrux && cargo build --releaseRun a first scan
Scan your project directory to get an initial quality score and treemap visualization.
sentrux /path/to/your/projectEstablish a quality baseline
Before a coding session, save a baseline snapshot so Sentrux can detect degradation introduced by subsequent changes.
sentrux gate --save .Configure architectural rules
Create a .sentrux/rules.toml file in your project root to define coupling limits, forbidden cycles, layer dependencies, and file-size constraints.
# .sentrux/rules.toml example
[coupling]
max_fan_out = 10
[cycles]
forbidden = true
[layers]
order = ["domain", "application", "infrastructure"]Add Sentrux to your MCP client config
Register Sentrux as an MCP server so your AI client can call its 9 tools: scan, health, session_start, session_end, rescan, check_rules, evolution, dsm, and test_gaps.
{
"mcpServers": {
"sentrux": {
"command": "sentrux",
"args": ["mcp"]
}
}
}Use gate to detect degradation after changes
After a coding session, run gate without --save to compare current state against the baseline and identify architectural regressions.
sentrux gate .Sentrux Examples
Client configuration
Claude Desktop configuration to use Sentrux as an MCP server for architectural analysis.
{
"mcpServers": {
"sentrux": {
"command": "sentrux",
"args": ["mcp"],
"env": {}
}
}
}Prompts to try
Example prompts leveraging Sentrux's MCP tools for architectural analysis.
- "Scan my project and give me the current quality score"
- "Check if there are any architectural rule violations in the codebase"
- "Show me where the test coverage gaps are in the project"
- "What modules have the highest coupling and should be refactored?"
- "Compare the current architecture against the baseline I saved before this sprint"
- "Run the evolution tool to show how code quality has changed over time"Troubleshooting Sentrux
GPU rendering fails with WGPU errors on the live treemap
Set the WGPU_BACKEND environment variable to force a specific backend: export WGPU_BACKEND=gl for OpenGL or export WGPU_BACKEND=vulkan for Vulkan. Alternatively run in CI mode with 'sentrux check .' which has no GUI dependency.
sentrux check exits with code 1 in CI unexpectedly
Review the rule violations printed to stdout. Rules defined in .sentrux/rules.toml trigger exit code 1 when violated. Either fix the violations or relax the rule thresholds in rules.toml.
MCP client cannot find the 'sentrux mcp' subcommand
Ensure the sentrux binary is on the system PATH available to the MCP client process. Verify with 'which sentrux'. You may need to provide the absolute path in the command field of the MCP config.
Frequently Asked Questions about Sentrux
What is Sentrux?
Sentrux is a Model Context Protocol (MCP) server that real-time architectural sensor that helps ai agents close the feedback loop, enabling recursive self-improvement of code quality. pure rust. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Sentrux?
Follow the installation instructions on the Sentrux GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Sentrux?
Sentrux works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Sentrux free to use?
Yes, Sentrux is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Sentrux Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Sentrux? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Thinkwatch
★ 967Enterprise AI bastion host for secure AI API and MCP access, with unified proxying, RBAC, audit logs, rate limiting, and cost tracking across OpenAI, Anthropic, Gemini, and self-hosted LLMs.
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Sentrux in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Sentrux?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.