Best Pos AI Skills & MCP Servers
280 curated Pos skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Bbpm
Burningbros BBPM MCP — Model Context Protocol server exposing the BB Project Management API to Claude. Create issues, assign tasks, comment, and query the board from a chat prompt.
Nordic Data
MCP server exposing Nordic Data API — company, VAT, sanctions, KYB and address data across 15 EU countries to AI agents
Server
Arguslog MCP server — exposes the full Arguslog API (issues, projects, orgs, alerts, releases, tier admin, …) as Model Context Protocol tools. Authenticate with a Personal Access Token from the dashboard.
Crypto Quant Signal
The Brain Layer for AI Trading Agents — composite quant calls across 5 exchanges (Hyperliquid, Binance, Bybit, OKX, Bitget), cross-venue arb, regime-aware classification, and a 20-skill catalog via MCP.
Terminal Pilot
MCP server that exposes terminal pilot automation as tools.
Pkistudiomcp
Local MCP server exposing PkiStudioJS ASN.1 and PKI key material tools.
Mcp
MCP (Model Context Protocol) server that exposes the entire @ar-agents/* toolkit (identity, mi-argentina, identity-attest, mercadopago, mercadolibre, whatsapp, banking, facturacion, shipping, boletin-oficial, igj, firma-digital) to any MCP host (Claude De
Server
MCP server for DWLF market analysis platform — exposes market data, indicators, signals, strategies, backtests, portfolio, trade journal, and more as AI-accessible tools
Server
MCP server for OpenWeb — the booking-grade reliability layer for AI agents. Self-host with docker-compose for free, OR set OPENWEB_BRAIN_URL + OPENWEB_BRAIN_KEY to point at the hosted brain.
Server
Vecto Model Context Protocol server — exposes /api/v1 as MCP tools + resources for Claude Code, Cursor, Claude Desktop, etc.
Brick Smartcontext
Composite brick — orchestrates smartread, cache, compress, tokenbudget, and overview to deliver optimal context within a token budget.
Sdl
Symbol Delta Ledger MCP Server - Cards-first code context for polyglot repositories
Local
SkillFM local — single npm package for the SkillFM platform on user nodes. Subcommand router exposes (1) Beacon MCP stdio server (cost-optimizer for any agent; merged in from @skillfm/beacon-mcp on 2026-05-01), (2) skill runtime (BYOK Playwright / brain r
Windy Word
MCP server exposing Windy Word's agent-control surface as 95 typed tools (paste / hotkeys / transcription / recording verbs / audio devices / voice clones / install / Doctor / archive / translation / documents / soul-file).
Docker
Universal Docker MCP server for AI assistants (Cursor, Claude Desktop)
Brick Aiteam
AI team coordination — loads dispatch, parallel, debate, review, agent for multi-agent orchestration.
Gateway
MCP Gateway for exposing VAT agents through Model Context Protocol
Cli
Research knowledge repository with semantic search, citations, and project lineage tracking
Agent
Traseq MCP server, CLI, and SDK for AI-assisted trading strategy research, SignalGraph authoring, validation, backtesting workflows, and system template composition.
Posterly
MCP server for posterly — schedule social media posts from Claude Desktop
Logosdb
MCP server exposing LogosDB semantic search to Claude Code and other MCP clients
Code Graph Rca
RCA infrastructure for AI-built code. Code knowledge graph + opinionated RCA engine, exposed via MCP (Cursor / Claude Code / Cody / Cline / Continue / Windsurf / Zed) plus CLI and library. RCA is the wedge; the same engine covers code review, refactor bla
Gemini Code Context
MCP server that gives Claude Code persistent memory of your codebase, backed by Gemini's 2M-token context. Includes eager `ask`/`code` for cached repo Q&A and `ask_agentic` for agentic file access on repos that exceed the model's input-token limit.
Polygraph
A Model Context Protocol server for coordinating cross-repository changes via Polygraph
About Pos skills on iClaude
iClaude is the universal install layer for AI skills. Every Pos skill on this page can be installed into Claude Code, Claude Desktop, Cursor, ChatGPT, n8n, Codex, and more — using a single copy-paste command. No config drift, no per-stack adapters, no manual MCP wiring.