@codapult/guard is local-first, model-agnostic architecture guardrail software for AI coding agents. Use it to detect architectural drift, enforce approved software architecture rules, and check code changes in JavaScript and TypeScript projects.

Security infrastructure your AI can't be — deterministic, current past your model's training cutoff, whole-repo-aware, author-independent. Security MCP for vibe coding. 634 rules, 39 tools, CLI + doctor. Prompt-level shift-left security (secure_prompt — e

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

Enables AI assistants to perform read-only scans of local projects, Git history, GitHub Actions workflows, machines, and GitHub accounts for supply-chain malware indicators, and to access cleanup and recovery guidance.

Enables clients to look up failure modes and corresponding procedures, search and retrieve entries, and build prompts or reviews through structured tools over stdio JSON-RPC.

🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI ready.

A free, read-only server that lets users diagnose production AI-agent risks: it flags over-privileged API keys from permission descriptions, scans code snippets for the signals that prevent duplicate execution, and explains guard patterns such as idempotency keys, approval gates, outboxes, and circuit breakers. It makes no network calls or writes, and rejects inputs that look like real secrets.

Guardian agent for AI coding: four frontier models review risky diffs and commits before they ship.

Enables MCP clients such as Claude to read temperatures, fan speeds, power and clocks from a CoolerControl daemon, and to change fan profiles, fixed duty speeds, modes, functions, alerts and custom sensors through its REST API. Write operations are gated behind a token with write access, with an optional minimum-duty floor guarding against accidentally stopping a pump or fan.

Enables controlled, human-style mouse, keyboard, and clipboard interaction with Windows applications through MCP tools for window inspection, safe activation, cursor movement, clicks, dragging, typing, scrolling, copy/cut/paste, background reading, and pause/resume safeguards.

Embeds a runtime MCP inspector in a NestJS app so coding agents can inspect the module and provider graph, routes and their guards/interceptors/pipes/filters, logs, request traces, event listeners, and scheduled jobs through an HTTP endpoint.

Enables AI clients to observe foreground browser viewports, read filtered page evidence, and run guarded reusable site-pack procedures through the same local runtime as the CLI.

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

Enables agents and terminal users to inspect ClickHouse over HTTP by listing databases and tables and running guarded read-only SELECT queries without modifying data.

Enables MCP clients to operate an already-logged-in Chrome tab through a browser extension and chrome.debugger, exposing navigation, page reading, interaction, screenshots, cookies/storage, network and console debugging, downloads, and batch actions under default-deny safety guards.

Prove that what already worked still works after an agent changed the code. Picture checks, guards for fixed bugs, a pre-release walkthrough, and known-good markers — as a CLI and as an MCP server.

Enables AI clients to preview, search, read, create, update, schedule, and unschedule Garmin Connect workouts using a local Garmin session, with guarded writes and a limited tool set. Supports running, cycling, cardio, and strength workouts without exposing generic API, filesystem, or shell access.

Enables MCP clients to explore PostgreSQL schemas, run guarded read-only queries with row limits, and inspect execution plans without executing them. It prevents writes and DDL while exposing schema discovery tools, a schema overview resource, and a guided analysis prompt.