Lets AI assistants run CodeScene Code Health reviews on a local codebase to find maintainability issues and technical debt.
Also known as codescene-oss/codescene-mcp-server, @codescene/codehealth-mcp
- Stars
- 85
- Tools
- —
- Downloads, 30 days
- 18,200
- Latest version
- 1.1.0
- Last commit
- Nov 13, 2026
- License
- —
What is CodeScene MCP?
CodeScene lets AI assistants run CodeScene Code Health reviews on a local codebase to find maintainability issues and technical debt.
Summary generated from the project's README
About CodeScene MCP server
Developers can use this server to integrate CodeScene Code Health analysis directly into their local AI workflows. By connecting tools like Claude Desktop, Cursor, or GitHub Copilot to your local codebase, you provide your AI assistant with deep insights into maintainability, technical debt, and design quality. The server runs entirely on your machine, ensuring that your source code and analysis data remain private and are never sent to external cloud providers or LLM vendors.
To get started, you can install the server via NPM, Homebrew, or as a VS Code extension. Depending on your needs, you can use a standalone license for local analysis or connect a CodeScene Core account via an access token to access advanced features like hotspots and code ownership. The server provides specific tools to help AI assistants identify complexity, deep nesting, or low cohesion, allowing them to perform targeted refactoring and verify if their changes actually improve the overall code health scores.
What you can do with it
- 1Preventing technical debt introductionAsk your AI assistant to flag maintainability issues like high complexity or deep nesting before committing new code.
- 2Guiding AI-driven refactoringDirect your AI assistant to perform modular refactoring by providing it with concrete design issues and measurable health scores.
- 3Analyzing legacy codebasesUse Code Health reviews to help an AI assistant understand real-world cognitive and design challenges within existing code.
- 4Monitoring MCP impactRequest a summary of how much your AI assistant has improved code quality through recent MCP events.
Written from the project's README. Every use case is checked against a quote from it.
How to install CodeScene MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall CodeScene MCP in Claude Code
$ claude mcp add codescene-mcp-server -- npx -y @codescene/codehealth-mcpInstall CodeScene MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"codescene-mcp-server": {
"command": "npx",
"args": [
"-y",
"@codescene/codehealth-mcp"
]
}
}
}Install CodeScene MCP in VS Code
.vscode/mcp.json
{
"servers": {
"codescene-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@codescene/codehealth-mcp"
]
}
}
}Install CodeScene MCP in VS Code CLI
$ code --add-mcp '{"name":"codescene-mcp-server","type":"stdio","command":"npx","args":["-y","@codescene/codehealth-mcp"]}'Install CodeScene MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"codescene-mcp-server": {
"command": "npx",
"args": [
"-y",
"@codescene/codehealth-mcp"
]
}
}
}Install CodeScene MCP in Codex
$ codex mcp add codescene-mcp-server -- npx -y @codescene/codehealth-mcpInstall CodeScene MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.codescene-mcp-server] command = "npx" args = ["-y", "@codescene/codehealth-mcp"]
Install CodeScene MCP in Gemini CLI
$ gemini mcp add -s user codescene-mcp-server npx -- -y @codescene/codehealth-mcpInstall CodeScene MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"codescene-mcp-server": {
"command": "npx",
"args": [
"-y",
"@codescene/codehealth-mcp"
]
}
}
}Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachablePass
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubCodeScene MCP Server
The CodeScene MCP Server exposes CodeScene's Code Health analysis as local AI-friendly tools.
This server is designed to run in your local environment and lets AI assistants (like GitHub Copilot, Cursor, Claude code, etc.) request meaningful Code Health insights directly from your codebase. The Code Health insights augment the AI prompts with rich content around code quality issues, maintainability problems, and technical debt in general.
The repository also includes a downloadable set of public agent skills in skills/ for teams that want to reuse CodeScene MCP workflows in their own agentic pipelines.
Getting Started with CodeScene MCP
Want AI to perform the setup? Start with skills/installing-and-activating-codescene-mcp/SKILL.md.
- Setting up Authentication to the MCP Server — see Authentication.
- Install the MCP Server using one of the installation options below.
- Add the MCP Server to your AI assistant. See the detailed instructions for your environment in the installation guide.
- Copy the agent guidance that matches your license into your repository: AGENTS-full.md for CodeScene Core users, AGENTS-standalone.md for standalone license users, or .amazonq/rules for Amazon Q. Also copy any relevant public skills for reusable workflow prompts.
- Explore the available tools to see what the MCP Server can do and which tools are available for your license.
Installation
Choose the installation method that works best for your platform.
Run the MCP server directly with npx (no install needed):
npx @codescene/codehealth-mcp
Or install globally:
npm install -g @codescene/codehealth-mcp
The first run automatically downloads the correct platform-specific binary for your system and caches it for future use. Requires Node.js 18 or later.
📖 Full installation & integration guide
Add the CodeScene marketplace and install the plugin:
/plugin marketplace add codescene-oss/codescene-mcp-server
/plugin install codescene@codescene
This installs the MCP server and Code Health skills. Requires Node.js 18 or later.
Download the MCP bundle from the latest release page:
codehealth-mcp-{version}.mcpb
Then open the .mcpb file with Claude Desktop to install the MCP server.
The CodeScene MCP is available as a VS Code extension:
brew tap codescene-oss/codescene-mcp-server https://github.com/codescene-oss/codescene-mcp-server
brew trust codescene-oss/codescene-mcp-server
brew install cs-mcp
📖 Full installation & integration guide
For VS Code / GitHub Copilot, the CodeScene MCP extension bundles and automatically configures the server without a separate PowerShell installation.
Run this in PowerShell:
irm https://raw.githubusercontent.com/codescene-oss/codescene-mcp-server/main/install.ps1 | iex
After installing, fully quit and reopen your AI assistant or IDE (including all VS Code windows) so it picks up the updated PATH, then configure the MCP server using the guide below. Restarting only the MCP server or an integrated terminal does not refresh VS Code's PATH. The guide also includes a VS Code configuration that uses the executable path directly and avoids this PATH requirement.
📖 Full installation & integration guide
Download the latest binary for your platform from the GitHub Releases page:
- macOS:
cs-mcp-macos-aarch64.zip(Apple Silicon) orcs-mcp-macos-amd64(Intel) - Linux:
cs-mcp-linux-aarch64.ziporcs-mcp-linux-amd64 - Windows:
cs-mcp-windows-amd64.exe
After downloading, make it executable and optionally add it to your PATH:
chmod +x cs-mcp-*
mv cs-mcp-* /usr/local/bin/cs-mcp
You can also build a static executable from source.
[!WARNING] The Docker distribution is being retired. From October 1 through December 31, 2026, Docker images will be released only for bug fixes. No Docker images will be released after December 31, 2026. Migrate to NPM / npx, Homebrew, the Windows installer, or another installation option above.
docker pull codescene/codescene-mcp
📖 Full installation & integration guide | Build the Docker image locally
Use Cases
[!TIP] Watch the demo video of the CodeScene MCP.
[!NOTE] CodeScene MCP comes with a set of example prompts, agent guidance files to capture the key use cases, and a downloadable set of public skills. Copy the agent guidance that matches your license — AGENTS-full.md for CodeScene Core users or AGENTS-standalone.md for standalone users — and any relevant skills to your own repository.
With the CodeScene MCP Server in place, your AI tools can:
Safeguard AI-Generated Code
Prevent AI from introducing technical debt by flagging maintainability issues like complexity, deep nesting, low cohesion, etc.
Uplift Unhealthy Code for AI Readiness
AI refactoring quality improves when code is modular and easy to reason about. The MCP server gives your assistant concrete guidance to get there:
- run focused Code Health reviews,
- identify the specific design issues to address,
- refactor in small, measurable steps, and
- verify progress with updated Code Health scores.
This workflow works with MCP alone and is often enough to safely improve legacy code.
Make Targeted Refactoring
AI tools can refactor code, but they lack direction on what to fix and how to measure if it helped.
The Code Health tools solve this by giving AI assistants precise insight into design problems, as well as an objective way to assess the outcome: did the Code Health improve?
Understand Existing Code Before Acting
Use Code Health reviews to inform AI-driven summaries, diagnostics, or code transformations based on real-world cognitive and design challenges, not just syntax.
Review MCP Safeguard Impact
Ask your AI assistant to show your MCP usage overview to see Code Health uplifts, prevented degradations, and the scope and quality of your latest 250 MCP events. Supported clients display an interactive dashboard; other clients receive a Markdown summary. This API-connected feature requires a CodeScene Core account and is not available with a standalone license. See show_mcp_usage_overview for details.
Frequently Asked Questions
The full feature set — including hotspots, technical debt goals, and code ownership — requires a CodeScene subscription. Authenticate by asking your AI Assistant to login to CodeScene, or use the login too. Alternatively, use your CodeScene instance to create the CS_ACCESS_TOKEN which activates the MCP.
The MCP supports both CodeScene Cloud and CodeScene on-prem.
For local Code Health analysis without a CodeScene subscription, you can use the standalone CodeScene Code Health MCP.
The CodeScene MCP Server runs fully locally. All analysis — including Code Health scoring, delta reviews, and business-case calculations — is performed on your machine, against your local repository. No source code or analysis data is sent to cloud providers, LLM vendors, or any external service.
Analysis results (e.g. hotspots and technical debt goals) are fetched via REST from your own CodeScene account using a secure token.
For complete details, please see CodeScene's full privacy and security documentation.
CodeScene MCP can work with any model your AI assistant supports, but we strongly recommend choosing a frontier model when your assistant offers a model selector (as in tools like GitHub Copilot).
Frontier models -- such as Claude Sonnet -- deliver far better rule adherence and refactoring quality, while legacy models like GPT-4.1 often struggle with MCP constraints. For a consistent, high-quality experience, select the newest available model.
Since you have to provide a mount path for Docker, you can either have a MCP configuration per project (in VS Code that would be a .vscode/mcp.json file per project, for example) or you can mount a root directory within which all your projects are and then just use that one configuration instead.
In our testing we've seen that IntelliJ's AI Assistant sometimes gives a wrong path to the CodeScene MCP server. From what we can tell, it seems to have nothing to do with the MCP server itself, but rather with IntelliJ's AI Assistant, which seems to hallucinate parts of the path some of the time. We're still investigating this issue and will update this section once we have more information.
If your organization uses an internal CA (Certificate Authority), set the REQUESTS_CA_BUNDLE environment variable to point to your CA certificate file (PEM format). The MCP server automatically configures SSL — you only need to set it once.
The MCP also supports SSL_CERT_FILE and CURL_CA_BUNDLE as alternatives.
For detailed configuration examples (including Docker certificate mounting), see Configuration Options — SSL/TLS.
The MCP server periodically checks GitHub for newer releases and shows a "VERSION UPDATE AVAILABLE" banner when your version is outdated. This check runs in the background and never blocks tool responses, but in network-restricted environments you may want to disable it entirely.
Set the CS_DISABLE_VERSION_CHECK environment variable to any non-empty value (e.g. 1). For setup details, see Configuration Options — Version Check.
Building from Source
The MCP server is written in Rust. To build from source:
cargo build --release
The binary is produced at target/release/cs-mcp.
For more details, see:
CodeScene MCP questions
How do I add CodeScene MCP to Claude Code?
Run claude mcp add codescene-mcp-server -- npx -y @codescene/codehealth-mcp in your terminal. Add --scope user to make it available in every project.
How do I add CodeScene MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Do I need a CodeScene account to use the MCP?
The full feature set requires a CodeScene subscription, authenticated via login or a CS_ACCESS_TOKEN. Local Code Health analysis is available without a subscription through the standalone CodeScene Code Health MCP.
Does the CodeScene MCP send my source code to the cloud?
No. The server runs fully locally and all analysis happens on your machine against your local repository; only analysis results are fetched from your own CodeScene account via REST.
Which LLM models work best with the CodeScene MCP?
Any model your AI assistant supports can work, but frontier models such as Claude Sonnet deliver better rule adherence and refactoring quality than legacy models like GPT-4.1.
How do I configure custom SSL certificates for the MCP server?
Set the REQUESTS_CA_BUNDLE environment variable to point to your internal CA certificate file in PEM format. SSL_CERT_FILE and CURL_CA_BUNDLE are supported as alternatives.
How do I install the CodeScene MCP server?
You can install it via NPM/npx, Homebrew, the Windows installer, Docker, or as a plugin or extension for Claude Code, Claude Desktop and VS Code; a manual binary download is also available.