MCP servers and skills: search, filter by where they run, and compare.
1–24 of 30 tools for “reviewer-proxy”
Clear allAgent Skill that reviews agent work on behalf of the user
SkillMITFew starsNo key
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action rec
GoApache-2.0★ 959No key
A multi-agent workbench for coding agents — orchestrate Claude Code, Codex, OpenCode & pi from a native macOS app, Telegram/Discord/iMessage, or voice. Per-project workspaces, worker teams, flow graph
SkillMIT★ 17No key
Open evidence profile for MCP tool actions. Enforce configured tool-call policies and record decisions and observations in offline-verifiable bundles. Optional Linux kernel controls. No hosted backend
SkillMIT★ 13No key
MCP server for on-premises Azure DevOps Server (TFS) with TFVC support - shelvesets, changesets, Work Items, Git, Pipelines, Test Plans, Wiki for AI assistants.
Node.jsMIT★ 16No key
Claude Code skill for adversarial code review - spawns a GPT‑5.6 Sol reviewer in a herdr split pane to attack your diff, then interrogates its findings before relaying verdicts.
SkillMIT★ 9No key
Open-source, tenant-isolated bridge connecting ChatGPT and Codex to user-owned Nextcloud via OAuth, MCP, WebDAV, and OCS.
PythonApache-2.0★ 2Few starsNo key
Claude Code plugin for token economy: the strongest model thinks, cheaper models grind. Pinned subagents (sonnet scout and implementer, haiku test-runner, opus reviewer), a routing skill, and a dispat
SkillMIT★ 4Few starsNo key
SkillMIT★ 7No key
An MCP proxy that makes the lethal trifecta structurally impossible — and publishes the benchmark, and the attacks that beat it.
PythonApache-2.0★ 1Few starsNo key
Terminal-native delegation for local CLI agents. Launch and message real agents in isolated tmux rooms—no API proxy or model adapters.
SkillMIT★ 6No key
把 AI 编程助手调教成学术科研搭子：反幻觉行为纪律 + 顶会论文全流程技能 + 文献检索 MCP | Turn your AI coding agent into an academic research copilot
SkillMIT★ 1Few starsNo key
Inline policy enforcement proxy for AI agents: OPA policies on MCP tool calls, human approval for risky actions, and a hash-chained audit ledger.
SkillApache-2.0★ 1Few starsNo key
Agent Skills for Claude Code & skills.sh — senior engineering-manager skill for Next.js 16 + React 19 + Supabase + Vercel
SkillMIT★ 7No key
Forge Cascade MCP Memory Server with route-first buyer, checkout, and proof metadata for enterprise AI memory.
DockerMIT★ 1Few starsNo key
MCP server that wraps Claude Code's code-review skill (5 parallel reviewer subagents, effort low-max, fix mode) — works with CC Switch / OAuth / API key on Windows & macOS
Node.jsMITFew starsNo key
SkillMIT★ 2Few starsNo key
生成 5:2 横向多风格高级概念封面图/海报候选图。用户说“生成封面：<url>”“生成封面：<内容>”“做封面图”“公众号封面”“X 封面”“concept cover”“cover image”时使用。 URL 输入必须先调用/遵循 qiaomu-markdown-proxy 读取原文完整 Ma
SkillMIT★ 3Few starsNo key
Stable HTTPS preview URLs for local dev and coding agents — one command, MCP-native, self-hostable
Node.jsMITFew starsNo key
An opinionated, testable AI code-review agent for GitLab: review policy as a skill, behavioral regression tests, external benchmark, sandboxed dev container, credential isolation, telemetry, and a web
SkillMIT★ 1Few starsNo key
SkillMITFew starsNo key
A Claude Code security plugin — PreToolUse hooks (block destructive commands, egress allowlist, secret-scan on write), a restricted security-reviewer subagent, and /security-review + /threat-model com
SkillMITFew starsNo key
One Agent Skills code-review standard for Claude Code, Codex, Devin and Factory Droid: bugs first, then repo conventions, verb+noun naming, SOLID, an over-engineering guard and a Spring/Apache-grade J
SkillMITFew starsNo key
AI Agent for Automated AWS Architecture Reviews Powered by Claude Code
SkillMIT★ 2Few starsNo key
Who stands behind it
