⌨️Cursor 必备 MCP 组合推荐

Interaction profile registry for AI agents. Log interactions, query behavioral lenses.

A legal home for AI agents: Wyoming $299 or Nevis LLC. Free diagnostic; agents pay in USDC/USDT.

Global weather via Open-Meteo: forecast, ERA5 archive, marine, air quality, geocoding, elevation.

Stdio MCP proxy: intercepts oversized tool results into a queryable embedded DuckDB.

Agent-to-agent Lightning commerce: buy, sell & discover files, data, APIs & compute. Non-custodial.

Honest voice authenticity for AI agents: enrol a voice, verify a call clip. Signal, not verdict.

Safe-by-default UniFi MCP: Network + Protect + Access, multi-site, dry-run, audit log.

Agentic API marketplace — search, provision, and call data sources with one Ozma key

Self-hosted MCP voice agent that places phone calls on your behalf via Retell.

Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.

MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR

Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine

Install the ContinueWith AI handoff widget from coding agents (Cursor, Claude Code, Codex).

Control QSC Q-SYS systems over QRC from AI agents or Claude.

AI lead discovery, qualification, and outreach prep on your Leadbay account.

Open, sourced, confidence-scored intelligence on AI startups - a free PitchBook alternative.

High-entropy alloy and oxide descriptors and phase-prediction rules, with provenance.

Architecture write-gate for AI agents: blocks code that violates your Hexagonal/DDD layer rules.

Create and manage Convertrilo video encoding jobs from MCP clients and agent workflows.

US open solar data for agents: PVWatts production, tariffs & ROI, market data, forecasts. 18 tools.

MCP server for the Cisco Meraki Dashboard: networks, devices, wireless, switch, appliance.

MCP server for Freshdesk — tickets, contacts, companies, agents, groups, and knowledge base.

Action1 MCP server — endpoint inventory, patch visibility, and policy automation via REST API.

Read-only MCP server for Inforcer M365 baseline governance, plus assessment runs.

Redacts PII/PHI from text before it reaches an LLM. Fail-closed, self-hosted, no egress.

20 SKILLs de auditoría interna para agentes de IA según IIA, COSO, NIST, ISO, COBIT y ACFE.

Geocode, reverse geocode, and run Overpass spatial queries on OpenStreetMap data.

Convert .eml email exports to Markdown with YAML front matter

Pure-Go browser for AI: fetch pages, render JS without Chromium, return clean Markdown over MCP.

Fleet-wide backup triage, stale-backup detection, and cross-engine analytics for any MCP agent.

Your agent opens a real merchant account (go_live) and takes payments the same day. 3.9% flat.

MCP server for lossless YAML 1.2 parsing, formatting, and validation (pure Rust).

Bitemporal memory for AI agents. SEC 17a-4 audit chain, GDPR crypto-shred, information barriers.

Real-time social media and prediction market integrity layer for traders, funds, and quant desks.

Deterministic Android app compiler — agents write a YAML model, the compiler emits the native app.

Live React design-system APIs, patterns, and code validation so AI agents build real UI, not slop.

Webhook & callback layer for AI agents: create a URL, wait_for_callback, and verify over MCP.

Phone carrier lookup, append, verification, DNC, and fraud data services.

A job-search companion: tailor your CV to a role, score fit, fix ATS issues. Also via MCP.

Inspect a site's AI-search readiness: AI crawler access, llms.txt, schema markup, meta directives

Validate commit messages, branch names, author info, push safety, and repo state.

Search dynamical.org's open STAC catalog of weather & climate datasets (GFS, ECMWF, HRRR).

1,407 pay-per-call tools + 100 skill packs. USDC on 6 chains or free via PoW.

An open-source API for collecting and managing contacts and signups.

Open-source, privacy-first web analytics for tracking your sites' traffic.

An open-source headless CMS for managing content models and entries.

Screen and score stocks with the Quality Screener engine: filters, custom scores, and history.

Persistent, read-only codebase memory for Claude Code; ask it instead of re-reading files.