MCP server that lets an AI coding agent verify its own edits: runs the project tests, linters and build, reports what failed
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
transport stdio counts 0 tools · 0 res
· 0 prompts
permission surface via code analysis
No tools enumerated yet for this server.
prompt-surface
shipped agent-instruction files + hidden-content / dangerous-code findings —
quoted from the analyzed source
analyzed commit 5ee334a · analyzer v28 · 1d ago
skills & prompt files 1
- agent-rules Conte777-verify-mcp-5ee334a/CLAUDE.md
evidence-backed
findings quoted directly from the published source artifact — not inferred
code files: 11
filesystem 3
- fs Conte777-verify-mcp-5ee334a/src/config.ts :1
import { existsSync, mkdirSync, readFileSync, writeFileSync } from "node:fs"; - fs Conte777-verify-mcp-5ee334a/src/handler.ts :1
import fs from "node:fs"; - fs Conte777-verify-mcp-5ee334a/src/runner.ts :2
import { existsSync, mkdtempSync, writeFileSync } from "node:fs";
shell / exec 1
- shell Conte777-verify-mcp-5ee334a/src/runner.ts :1
import { spawn } from "node:child_process";
install hooks 2
- prepare Conte777-verify-mcp-5ee334a/package.json :31
lefthook install && npm run build - prepublishOnly Conte777-verify-mcp-5ee334a/package.json :32
npm run typecheck && npm test
declared dependencies 7
- @modelcontextprotocol/sdk@^1.29.0
- zod@^4.4.3
- @biomejs/biome@^2.5.2
- @types/node@^26.1.0
- lefthook@^2.1.1
- tsx@^4.22.5
- typescript@^6.0.3