CodeScene
The CodeScene MCP Server exposes CodeScene’s Code Health analysis as local AI-friendly tools.
What is CodeScene?
CodeScene is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to codescene mcp server exposes codescene’s code health analysis as local ai-friendly tools.
The CodeScene MCP Server exposes CodeScene’s Code Health analysis as local AI-friendly tools.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The CodeScene MCP Server exposes CodeScene’s Code Health ana
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @codescene/codehealth-mcpManual Installation
npx -y @codescene/codehealth-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use CodeScene
CodeScene MCP Server exposes CodeScene's Code Health analysis engine directly to AI coding assistants, enabling them to evaluate the quality and maintainability of code in real time. It surfaces metrics like complexity hotspots, technical debt, code ownership patterns, and delta reviews so that AI tools like Claude can factor code health into refactoring suggestions and new code generation. Teams use it to prevent the accumulation of technical debt by giving AI assistants immediate, quantitative feedback on the health of every piece of code they touch.
Prerequisites
- Node.js 18+ and npx available on your system
- A CS_ACCESS_TOKEN from your CodeScene instance (required for authenticated analysis)
- Access to a CodeScene server (cloud or self-hosted)
- An MCP-compatible client such as Claude Desktop, VS Code, or Claude Code
Obtain a CodeScene access token
Log in to your CodeScene instance and generate an access token from your account settings. This token authenticates the MCP server's requests to CodeScene's analysis APIs.
Install the MCP server
Install the CodeScene MCP package globally via npm, or use npx to run it on demand without a permanent install.
npm install -g @codescene/codehealth-mcp
# Or use directly without install:
npx -y @codescene/codehealth-mcpConfigure your MCP client
Add the CodeScene server to your MCP client configuration file, providing your access token as an environment variable.
{
"mcpServers": {
"codescene": {
"command": "npx",
"args": ["-y", "@codescene/codehealth-mcp"],
"env": {
"CS_ACCESS_TOKEN": "your-codescene-access-token"
}
}
}
}Handle custom SSL certificates (if self-hosted)
If your CodeScene server uses an internal certificate authority, point the MCP server to your CA bundle via environment variables to avoid SSL errors.
{
"env": {
"CS_ACCESS_TOKEN": "your-token",
"REQUESTS_CA_BUNDLE": "/path/to/your/ca-bundle.pem"
}
}Restart your MCP client
Save the configuration file and restart Claude Desktop (or your chosen MCP client) for the new server to be recognized and its tools to become available.
Run a code health check
Open a conversation in your AI client and ask it to analyze a file or function. The AI will invoke CodeScene's analysis tools and return health metrics and improvement suggestions.
CodeScene Examples
Client configuration
Claude Desktop configuration for the CodeScene MCP server using npx with an access token.
{
"mcpServers": {
"codescene": {
"command": "npx",
"args": ["-y", "@codescene/codehealth-mcp"],
"env": {
"CS_ACCESS_TOKEN": "cs_tok_xxxxxxxxxxxxxxxx"
}
}
}
}Prompts to try
Example prompts that leverage CodeScene's code health analysis through your AI assistant.
- "Analyze the code health of src/payment/processor.py and tell me the biggest maintainability issues."
- "Which files in this repository are the biggest technical debt hotspots?"
- "I'm about to refactor this module — what code health issues should I address first?"
- "Review the changes in my current branch and flag any increases in complexity."
- "Explain the ownership patterns for the authentication module — who knows it best?"Troubleshooting CodeScene
"Unauthorized" or 401 errors when running analysis
Verify that CS_ACCESS_TOKEN is set correctly in the env block and matches a valid token from your CodeScene dashboard. Tokens are instance-specific, so make sure the token belongs to the correct CodeScene server.
SSL certificate errors when connecting to a self-hosted CodeScene instance
Set REQUESTS_CA_BUNDLE, SSL_CERT_FILE, or CURL_CA_BUNDLE in the env block to point to your organization's CA certificate in PEM format. All three variable names are supported.
MCP server starts but no CodeScene tools appear in the AI client
Run 'npx -y @codescene/codehealth-mcp' directly in a terminal to see startup errors. A missing or invalid CS_ACCESS_TOKEN is the most common cause. Also ensure you're on a supported Node.js version (18+).
Frequently Asked Questions about CodeScene
What is CodeScene?
CodeScene is a Model Context Protocol (MCP) server that codescene mcp server exposes codescene’s code health analysis as local ai-friendly tools. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install CodeScene?
Install via npm with the command: npx -y @codescene/codehealth-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with CodeScene?
CodeScene works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is CodeScene free to use?
Yes, CodeScene is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
CodeScene Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to CodeScene? 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.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
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 CodeScene 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 CodeScene?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.