Predictive Debugger
Website and docs: predictivedebugger.dev
MCP server for finding likely runtime failures in JavaScript and TypeScript.
Seven tools help your coding agent check types, rank risky files, trace dependencies, inspect
logs and get an independent model review with a line number and reason.
Uses the Claude Code, Codex or GitHub Copilot CLI you already have installed.
Prediction calls use that CLI's model access and usage allowance. No separate
API key is needed. Your provider's terms apply to those calls; check them before
use, especially on a Claude subscription. See Provider terms.
Setup
Requires Node.js 22 or later. For model predictions, install
and sign in to at least one supported CLI. Python 3 is optional for log analysis.
1. Add the MCP server
Choose your agent below. npx downloads and runs the package automatically.
Claude Code
Run in your project on macOS, Linux or WSL:
claude mcp add --scope project predictive-debugger -- npx -y predictive-debugger@latest
On native Windows, from PowerShell:
claude mcp add --scope project predictive-debugger -- cmd /d /c npx -y predictive-debugger@latest
Use --scope user to make it available in every project.
Codex
For a user-level setup on macOS, Linux or WSL:
codex mcp add predictive-debugger -- npx -y predictive-debugger@latest
On native Windows, from PowerShell:
codex mcp add predictive-debugger -- cmd /d /c npx -y predictive-debugger@latest
For project-only setup or a longer startup timeout, see
Codex configuration.
GitHub Copilot CLI
Add to .mcp.json in your project:
{
"mcpServers": {
"predictive-debugger": {
"command": "npx",
"args": ["-y", "predictive-debugger@latest"],
"tools": ["*"]
}
}
}
On native Windows, use "command": "cmd" and
"args": ["/d", "/c", "npx", "-y", "predictive-debugger@latest"].
For every project, see Copilot user-level setup.
2. Check the connection
Restart your agent and check /mcp for predictive-debugger and its seven tools.
To check that the package downloads and print its version:
npx -y predictive-debugger@latest --version
Running without --version starts a stdio server that waits for your agent's
messages. See setup help for local builds and troubleshooting.
3. Ask your agent about the code
Use Predictive Debugger to find the riskiest files in src/.
Show the imports and tests connected to src/services/orders.ts.
Check src/services/orders.ts for likely runtime failures.
Find unusual entries in logs/app.log.
| Tool | What it does | Model call |
|---|
scan_project | Rank source files by risk density. Excludes tests by default. | No |
analyze_file | Return complexity metrics, risk scores and contributing signals. | No |
check_types | Return selected files' TypeScript compiler diagnostics using local project settings. | No |
map_dependencies | Find imports, reverse imports and connected test files, with source-line evidence. | No |
analyze_logs | Return log anomalies, ranked by severity and unusual wording. | No |
predict_failures | Get an independent model verdict with a line number, reason and confidence. Supports batches. | Yes |
list_providers | Check which supported CLIs are installed and their sign-in status. | No |
Start with scan_project and check_types, then read the files they highlight. Use
map_dependencies to find related files and predict_failures when you want a
second opinion. Pass several paths as files so small files share bounded model
calls and avoid repeating the CLI context for every file.
See the tool reference for parameters, result fields and limits.
How the server asks agents to verify new code
The server's MCP instructions ask agents to check code they wrote in the current
session from a fresh context. The routing depends on file count:
| Change | Requested check |
|---|
| One file, including a feature contained in one file | A fresh predict_failures call |
| Several files | A sub-agent scoped to the changed files and intended behavior, where the host supports it |
| Mechanical correction with one clear answer | Neither check required |
Grouped predictions retain per-file verdicts. They do not verify a feature's
requirements. The benefit of the sub-agent rule has not been measured.
Privacy and limits
- Static analysis, dependency maps and log analysis run locally.
predict_failures
sends source and bounded dependency context to your CLI's model provider.
Set calleeContext: false to omit dependency context.
- Credentials stay with the CLI. MCP tools can read paths the server process can
access; project-scoped setup does not restrict file access. See the
security model.
- JavaScript and TypeScript are supported, including JSX, TSX and decorators.
Vue and Svelte single-file components are not supported. Files above 4 MB are
rejected; large predictions may cover only selected declarations.
- Risk scores and predictions can be wrong. The benchmarks
use development cases and do not establish accuracy on arbitrary repositories.
- Manually verified on Windows. CI covers Windows, macOS and Linux on Node 22
and 24; real CLI installations on macOS and Linux have not been manually verified.
VS Code preview
An unfinished extension can show findings in the Problems panel. It requires a
local build and is not available on the Marketplace or as a prebuilt VSIX.
See trying the extension.
Documentation
License
MIT.