Developer Tooling

CI for MCP servers: schema contract testing + cross-model regression evals for your agent-facing tools

Git Helper Ai MCP Server by MEOK AI Labs

MCP server for auditing Git repositories against software engineering standards

The snippet manager for AI agents — a verified, safety-checked command library for Claude Code, Cursor, and any MCP client. Also a fast terminal-native CLI with TUI.

[](https://www.npmjs.com/package/@lacolaco/acl)

BCS fork of GitLab MCP server for pipelines, repositories, merge requests, issues, and content masking

MCP server for browser inspection with Puppeteer - network monitoring and console error tracking

MorphixAI MCP Server — connect AI agents (Claude Code, Cursor, Windsurf) to GitHub, GitLab, Jira, Notion, Gmail, Outlook, Figma, and 40+ workplace tools.

Black-box security & contract testing for MCP servers — rug-pull, tool-poisoning, schema-drift & protocol checks for CI (JUnit + SARIF).

Self-correcting 7-stage agent reasoning loop (SENSE→GKP→DECIDE+ACT→CHALLENGE-TEST→UPDATE→LEARN→REPORT). MCP server + CLI that scaffolds instruction files for GitHub Copilot, Cursor, and Claude Code.

Agent-agnostic development harness for AI coding agents — gated phase pipeline with a next-step trajectory engine, built-in MCP server, craft skills library, and deterministic gate validation. Works inside Claude Code, Codex, Cursor, VS Code, and any MCP-

AWS Network MCP Server – VPC inspection, security group analysis, ENI details, flow log queries, and IP address lookup for security investigations

Git worktree orchestration for parallel AI coding agents — isolated worktrees, auto rebase-merge, and smart conflict routing. 多 Agent 并行编码的 Git 编排层。

Advanced n8n AI Agent node for Claude, OpenAI & Gemini — native PDF/image vision, Claude Max (Claude Code OAuth) support, Anthropic prompt caching, structured output with auto-fix, fallback models, and on-demand document fetch.

The CLI agent that does nothing. Perfectly. A satirical, side-effect-free npm package — no filesystem access, no network calls, always exits 0.

Shell-wrapper hook binaries — agent-agnostic command gating via shell-AST. Decisions surface through stdout/stderr/exit-code; works for any caller (agent, human, CI).

MCP server for Claude Code — query AI rule violations, coding standards, and analytics directly in your IDE. Model Context Protocol.

Jenkins MCP server — manage jobs, builds, logs and CI/CD pipelines via AI

MCP server for pkgpulse: dependency intelligence for AI coding agents via x402 (USDC on Base). npm package health scores, typosquat/hallucination checks, and whole-package.json dependency audits — pay per call, no API key.

Lumin observability + Agent Firewall for OpenClaw — captures prompts, responses, tool I/O, and synchronously enforces firewall policies on every tool call.