Dependency graph & blast-radius analysis for TypeScript/JS. Predict breaks before commit.
{
"mcpServers": {
"io-github-vk0dev-code-impact-mcp": {
"command": "<see-readme>",
"args": []
}
}
}No install config available. Check the server's README for setup instructions.
Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Dependency graph & blast-radius analysis for TypeScript/JS. Predict breaks before commit.
Is it safe?
No package registry to scan.
No authentication — any process on your machine can connect.
License not specified.
Is it maintained?
Commit history unknown.
Will it work with my client?
Transport: stdio. Works with Claude Desktop, Cursor, Claude Code, and most MCP clients.
No automated test available for this server. Check the GitHub README for setup instructions.
No known vulnerabilities.
This server is missing a description. Tools and install config are also missing.If you've used it, help the community.
Add informationHave you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
A Model Context Protocol (MCP) server and CLI that provides tools for agent use when working on iOS and macOS projects.
XcodeBuildMCP provides tools for Xcode project management, simulator management, and app utilities.
An open-source AI agent that brings the power of Gemini directly into your terminal.
The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps.
MCP Security Weekly
Get CVE alerts and security updates for io.github.vk0dev/code-impact-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
CodeImpact MCP helps you answer a practical question before changing code: what else is likely to move if I touch this file?
It builds a dependency graph for a local TypeScript/JavaScript repo, then exposes a small set of read-only MCP tools for:
Current status: local-first and dogfooded, not published yet.
get_dependenciesFor one file, returns:
analyze_impactFor one or more changed files, returns:
gate_checkFor one or more changed files, returns a bounded recommendation:
PASSWARNBLOCKThis is a graph-only heuristic, not a full engineering safety system. It does not know about tests, runtime behavior, data migrations, or production traffic.
cd ~/projects/code-impact-mcp
npm install
npm run build
Development mode:
npm run dev
Compiled server mode:
npm run build
npm start
Optional quick transport smoke check after the server is up:
npm run smoke
npm test
npm run build
Focused graph/tool verification:
npx vitest run tests/graph.test.ts tests/tools.test.ts
The simplest honest first run is:
get_dependenciesanalyze_impact on a likely change targetgate_check for a quick pass/warn/block signalExample target repo from local dogfooding:
~/projects/openclaw-tasksExample progression:
get_dependencies for src/routes.tsanalyze_impact for src/routes/index.tsgate_check for the same file with a chosen thresholdget_dependencies
{
"projectRoot": "/Users/you/projects/openclaw-tasks",
"file": "src/routes.ts"
}
analyze_impact
{
"projectRoot": "/Users/you/projects/openclaw-tasks",
"files": ["src/routes/index.ts"]
}
gate_check
{
"projectRoot": "/Users/you/projects/openclaw-tasks",
"files": ["src/routes/index.ts"],
"threshold": 0.2
}
projectRoot should be an absolute path to the repo rootsrc/routes.tstsconfigPath is optional and should be relative to projectRootThe graph currently supports:
require(...).js import specifiers that point back to .ts source filesThe tool layer returns bounded JSON errors instead of crashing for:
tsconfigThe current riskScore is a simple graph-derived heuristic based on how many files are affected relative to graph size.
Treat it as:
gate_check recommendationPASS means low graph impact right nowWARN means review is recommended before proceedingBLOCK means the current change shape looks too risky for the chosen thresholdA good mental model is: CodeImpact tells you where to look next, not whether the code is truly safe.