Documentation
Quickstart, task guides with real tool output, and the full tool reference for the Predictive Debugger MCP server.
Predictive Debugger is an MCP server that ranks where your JavaScript and TypeScript is most likely to fail, then asks an independent model to name the failure. New here? Start with the quickstart - install, connect, and read your first scan in about five minutes.
Start
Guides
- Review code your agent just wroteCheck a change from outside the context that produced it, using a fresh prediction for one file or a scoped sub-agent for several.
- Find the riskiest file before a releaseRank a directory by risk density, read the signals behind the ranking, and understand what the numbers do and do not claim.
- Trace what a change breaksFind a file's imports, reverse imports, and connected tests with source-line evidence, so a local edit gets a review as wide as its reach.
Reference
- Advanced setupProvider login, registration scope, Codex and Copilot configuration, updates, and building Predictive Debugger from source.
- Tool referenceParameters, outputs, and limits for all six Predictive Debugger MCP tools, and how the prediction score is calculated.
- VS Code previewRun the experimental Predictive Debugger VS Code extension from source and configure its settings.
At a glance
| Package | predictive-debugger on npm |
|---|---|
| Version | 0.8.1 |
| License | MIT |
| Runtime | Node.js 22 or later |
| Languages | JavaScript and TypeScript, including JSX, TSX and decorators |
| Agents | Claude Code, Codex, and GitHub Copilot CLI |
| Tools | scan_project, analyze_file, map_dependencies, predict_failures, analyze_logs, list_providers |
| Cost | The MCP server is free. Predictions use your own CLI sign-in and its allowance. |
| Scope | Predictive Debugger ranks risk and predicts likely runtime failures. It does not run your code, and it does not replace tests or review. |
For agents
Every page here is also available as plain Markdown: append .md to any docs URL, for example /docs/tools.md.llms.txt indexes the site, and llms-full.txt contains the complete documentation in one file.