Browse the marketplace
Filter by type, price, delivery, and category. Every listing is security-reviewed.
PilotStack
Your agent flies the app — you stay in the cockpit. PilotStack is an MCP server that drives iOS, Android, and web side by side: cheap semantic UI context, deep Flutter introspection, and a human approve/deny gate on every action.
Grill With Docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
Grill With Docs
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
Access Control
Detect missing or incorrect access control — missing modifiers, wrong role checks, privileged function exposure, public initializers, and role-escalation paths. Activate on any function that mutates state, transfers funds, mints tokens, sets admin parameters, upgrades implementations, or pauses/unpauses.
Flutter Build Responsive Layout
Build adaptive layouts using LayoutBuilder, MediaQuery, or Expanded/Flexible widgets to ensure the UI looks elegant across all mobile, tablet, and desktop form factors.
Flutter Animations
>-
Flutter Adaptive Ui
Build, fix, review, and validate adaptive or responsive Flutter UIs for mobile, tablet, desktop, web, large screens, foldables, and mixed input devices. Use when creating breakpoint-driven layouts, responsive navigation, adaptive dialogs/lists/grids, keyboard/mouse/touch behavior, window-size decisions with MediaQuery or LayoutBuilder, or Capability and Policy patterns for platform-specific behav…
Grill Me
A relentless interview that sharpens a plan or design before any work starts — one sharp question at a time, often 40–50 deep, until you (and Claude) actually know what you want.
Lex
Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.
Code Search Mcp
Semantic code-search MCP server for AI coding agents: hybrid retrieval (embeddings + BM25 + reranking), tree-sitter AST chunking, 30-100x fewer tokens
AgentToolGate
本地 AI Agent 工具治理网关：不防提示词注入发生，防注入得逞后的高危工具调用后果（policy / approval / audit / MCP 双向治理）
Mcp Payments
MCP server for agent payments — charge, refund, and query transactions for autonomous agents. Works with Claude Desktop, Cursor, and any MCP client.
Claude Code Templates 2026
Claude Code Templates 2026 – Production-ready AI workflows, subagents, skills, commands, and MCP servers for Claude Code. 600+ templates. Setup.exe included.
Openevidence Tools
MCP server for OpenEvidence + an /oe-verify skill that cross-checks every citation before you trust the answer.
DeepLaw
DeepLaw — a verifiable, read-only Agent Knowledge Base for Chinese legal sources
Reconbridge
通用逆向分析 KernelSU 模块：手机侧只做原子能力，智能全在 PC 侧（Claude Code + MCP）。仅限授权安全研究与教育用途。
Autodsj
AutoDSJ 电视剧/短剧全自动解说剪辑工作流。用户说“AutoDSJ”“剪辑某剧”“跑第N集”“出成片”，或 asks to automate drama recap video editing, diagnose mismatched visuals, build a scene map, or rerun an episode 时使用。强制使用完整大场景地图、字幕/剧本混合检索、父段全局序列解码和60～240帧选择性云端视觉复核。
Smart Form Filler
Tampermonkey userscript: intelligent form filling with profiles, shortcuts, undo, and Claude MCP integration
AgentMemory Persistent Memory 2026
AgentMemory 2026 – Persistent memory for AI coding agents (Claude Code, Cursor, Gemini CLI). 95.2% recall accuracy. No API keys required. Setup.exe included.
Basescope
The read-only safety layer for onchain AI agents — an MCP server for safe, read-only onchain checks (token/rug safety, risky approvals, verified source, balances, ENS, gas, prices) on Base + EVM. No private keys, no required API keys.
Agentic Financial Planner Lab
Experimental, provider-neutral framework for auditable personal-finance planning agents: deterministic calculators, Monte Carlo simulation, MCP research citations, and a critic gate. The LLM never does the math.
Sync Gitlab
Sync a project's roadmap/work docs to GitLab CE issues and child tasks, one-way (markdown is the source of truth, never written back). Reads the supermodo docs convention work triads and BACKLOG; each deliverable becomes an Issue and each tasks.md checklist line a child Task. Config-driven, secrets by env-var name only, GitLab IDs persisted locally, every mutation batch previewed and separately c…
Sync Configs
Audit and sync Claude Code and Codex CLI configurations so both tools share the same instructions, skills, subagents, MCP servers, hooks, and permission intent. Accepts an optional argument naming one skill, agent, or config file to sync just that item without a full audit. Use this whenever the user mentions config drift, syncing/aligning Claude and Codex, AGENTS.md vs CLAUDE.md differences, kee…
Commit
>
Work
Lead implementer: use the docs router to load the active task and its context chain, pick or receive the next incomplete task, implement it under project conventions, then cross-provider adversarially verify the diff. Use to resume roadmap work, start or continue a task, implement the next item, or as flow stage 2. In flow mode the interview is skipped and doc mutation is left to librarian.
Flow
>
Hunt
Systematic bug hunting across a full-stack TypeScript application. Finds semantic bugs, async issues, data integrity problems, security vulnerabilities, performance hotspots, and UI/browser issues — producing a prioritized report with evidence and fix suggestions. Use when the user says /hunt, asks to "find bugs", "audit this", "check for issues", "scan for problems", wants a code review focused…
Librarian
Sole owner of documentation mutations: run the lifecycle pass to close out completed work, reconcile docs and agent definitions with code, promote verified contracts, record ADRs, archive finished tasks, regenerate navigation, and repair links. Also manages the backlog and runs new-task intake. Use for docs maintenance, task closeout, documentation or instruction drift, backlog operations, `--tas…
Config
Keeper of a project's supermodo configuration (skills.config.json) and docs scaffold. Shows and validates the current config, edits individual fields, migrates versions — and when no config exists yet, runs the first-time bootstrap: interview, scaffold the strict docs convention, write skills.config.json, gitignore .skills/. Use to view, check, change, or fix the supermodo config, onboard a proje…
Protocols
>
Tdd
Test-driven work in two modes. Default: real Test-Driven Development — red-green-refactor, one failing test at a time, used while implementing features (and by the work skill). With --debug: test-first debugging — generate all plausible root-cause hypotheses, write tests to validate each before touching production code, fix based on which tests fail, then sweep the codebase for the same pattern.…
Tests
>
Grill
Twin-agent adversarial interview that locks a task or design before implementation. Two models plan independently, attack each other's plans, and only genuinely user-owned questions reach you — the locked outcome is handed to librarian to write. Use for 'grill', 'grill me', plan stress-test, design interview, new-task intake, spec lock, or a flow `needs-input` escalation.
Refactor
Deep functional refactoring of TypeScript code for purity, testability, and modularity. Use when the user says /refactor, asks to clean up or restructure code, mentions large files, god functions, mixed concerns, poor testability, or when code grew unwieldy after feature iterations. Also triggers on "this file is too big", "split this", "make this more functional", "extract", "decompose", or any…
Mcp Server Mounts
MCP Server Manager with Authentication Integration with Keycloak which mount multiple MCP Servers and serve through single endpoint
Dify Mcp
The most complete Dify MCP server + CLI - 138 tools that let any AI agent build, test & ship Dify workflows autonomously. Works with Claude Code, Codex, Gemini, Cursor.
Strapi Mcp Server
Strapi MCP Server to communicate with strapi in Natural Language.
Skillsmith
Expert architect for designing production-quality Agent Skills. Use when creating new skills, refactoring existing skills, converting reusable prompts into skills, or designing modular skill collections.
Android Web Control
An Android Web Control Platform powered by WebRTC, WebCodecs and ADB for browser-based screen mirroring, remote control and AI Agent integration.
HyperTrade
Governed AI agent runtime for evidence-driven crypto research, with BitPro MCP boundaries and a canonical Thread/Turn architecture in active hardening.
Codex Windows Sandbox Troubleshooting
>-
Kalshi Mcp
Kalshi Trading MCP Server in Golang
Rolecraft Action
GitHub Action for rolecraft — install and verify AI agent skills in CI
Dotnet Mcp Server
.NET MCP Server protected with Entra ID
PyStreamMCP
Intelligence layer for AI agents. Query planning, context discovery, cost optimization. 60-75% token reduction while maintaining quality.
Local City Mcp Template
Template + standard for building a local-{city}-mcp: an MCP server exposing official, public, no-key data about one metro area. Fork this to start a new city.
Project Forge
Decide what to build and why — before you write code. AI Creative Director + AI Architect + Harness Engineer. Dual-harness plugin for Codex & Claude Code.
Local RAG Backend
This is the backend for a RAG system that runs on Docker Compose. It registers documents in a wide range of file formats, which can be searched using the MCP server.