Best Irs AI Skills & MCP Servers

Local-first, LLM-agnostic memory layer for AI assistants. Run via npx @psraghuveer/memento.

Local-first web intelligence MCP server for AI coding agents

Information-geometric agent memory with mathematical guarantees. 4-channel retrieval, Fisher-Rao similarity, zero-LLM mode, EU AI Act compliant. Works with Claude, Cursor, Windsurf, and 17+ AI tools.

LMCP — connect Claude Desktop, Cursor, Windsurf to Mail, Calendar, Contacts, Teams, OneDrive on macOS. Privacy-first: all data stays on your Mac.

The local-first falsifiable decision ledger — MCP server that turns an Obsidian vault into a compounding decision system with multi-model AI council dissent and outcome-driven refutation propagation.

Prism Coder — Cognitive memory + tool-calling intelligence for AI agents. Mind Palace persistent memory (BFCL Gold Certified, 100% Tool-Call Accuracy, 54 Agent Skills, Zero-Search HDC/HRR retrieval, HIPAA-hardened local-first storage, SLERP-optimized GRPO

Governance-first recursive cognition infrastructure — LuisCore Chorus Field MCP client + agent CLI (bootstrap, post, feed)

Your personal AI runtime, local-first. Patchwork OS gives any AI model a consistent set of tools, YAML recipes, a delegation policy with approval queue, and a durable trace memory — all on your machine, all under your policy.

Local-first personal productivity MCP server for Claude, Cursor, and any MCP client. Email, Calendar, Messaging, Search, Image Generation. BYOK, no cloud, no signup.

Opinionated MCP for Bear Notes. Relevance-ranked search across titles, bodies, hierarchical tags. Offline-first.

Safety first. Hardware-verified DeFi for AI agents — designed for when the AI can be compromised.

Modular MCP Server for multi-AI assistant coordination

Local-first MCP server for Claude Code cost analysis, budgets, forecasts, anomalies, and subagent-aware optimization from local JSONL session logs.

API-first MCP server for multi-model cross-review with unanimous convergence gates.

MIT-licensed MCP bridge to the Alethia runtime — the patent-pending zero-IPC E2E test runtime for AI agents. 2-5x faster than Playwright MCP. Signed evidence packs, EA1 fail-closed safety gate, WCAG + NIST 800-53 audits built in. Local-first, zero telemet

Unified npm bootstrap for the Yaver agent, SDK injection, and local-first developer runtime

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.

MCP executor for Claude Code or Codex with an npm-first launcher and cheaper local or flat-rate execution by default

JS reverse engineering MCP server with agent-first tool design and built-in anti-detection. 为 AI Agent 设计的 JS 逆向 MCP Server，内置反检测。

Local-first project memory for AI coding agents.

Local-first MCP server for cross-agent AI memory. One SQLite + FTS5 corpus across Claude Code, Cowork, Cursor, Continue, Zed, Obsidian, and Telegram — passively captured, verbatim, searchable from any MCP-compatible client.

First MCP wellness server for HUMANS and AI AGENTS. Pay-per-call wellness micro-content (18 formats × 20 languages × 2 audiences), settled in USDC on Solana via x402.

Agent-native TypeScript framework for building MCP servers. Declarative definitions with auth, multi-backend storage, OpenTelemetry, and first-class support for Bun/Node/Cloudflare Workers.

CLI-first infrastructure intelligence platform — analyzes DynamoDB, PostgreSQL, MySQL, MongoDB, SQS, SNS, SSM, Secrets Manager, Lambda, CloudWatch Logs and exposes findings as an MCP server for Claude Code