Best Irs AI Skills & MCP Servers

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

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

Local-first web intelligence MCP server for AI coding agents

Agent-first MCP server: AI coding agents find, compare, verify, and stack-build the right open-source tools across 35+ registries (npm, PyPI, Cargo, Maven, Go, RubyGems, NuGet, Hex, Composer, and more). Graph-aware ranking + version-aware compatibility in

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.

Local-first code intelligence CLI for unerr

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

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

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

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

User stories as structured AI coding context — scope-check via get_active_story (Claude Code, Cursor, Windsurf)

MCP-first devtools for AI agents.

Local-first MCP server that gives AI coding agents a living, browser-viewable project wiki and a project-local memory store, so the agent stays oriented and the human stays in control.

MCP-first browser primitives for AI agents — real eyes and hands on the web. Local-first. Vendor-agnostic. Yours to own.

CLI + MCP sentinel for engineering standards — SOLID, testing, architecture, CI/CD — auto-tailored to your stack. Minimal MCP footprint (~200 tokens) via CLI-first design.

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

Agent-first MCP server for WeChat Mini Program debugging, automation, and lightweight testing

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.

Frenchie — your agent's best friend. MCP-first multimodal Kit, Method workflow toolkit, and stdio MCP server for agents: OCR, transcription, file extraction, image generation, and product development process.

Turn editor chat history (Cursor, Claude Code, Windsurf, Copilot) into typed Markdown decisions + AGENTS.md rules — local-first, git-trackable, zero remember() calls.

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

Bounded conventions map and local-pattern discovery for AI coding agents. Local-first MCP server with AST-backed hybrid search.

Local-first code intelligence — MCP server for Claude Code, Cursor, Windsurf, Zed. Symbol graph, blast-radius, git-pinned memory. 43× fewer tokens than naive grep on the public bench. MIT, zero-config.