📁文件系统 MCP 推荐

AI contract review, clause drafting, compliance checklists & legal research.

HIPAA-aware healthcare AI. Clinical documentation, compliance checks, audit prep. Free local tier.

AI security scanning and trust scoring. Stack-specific threat models. Free local scan.

Personal knowledge graph AI memory. 15 tools, 89 actions. Emotional intelligence, CRM, social.

A sandboxed MCP tool for reverse engineering with multiple tool integrations

Search Canadian case law, browse legislation, and check citations via the CanLII API.

MCP server for read-only Linux system administration, diagnostics, and troubleshooting

Add authentication to your app without leaving your IDE.

Personalised AI augmentation system — makes you better at your work, not dependent on AI

Search and browse a curated gallery of memes, infographics, and visual content.

Brivvy MCP (OAuth): on-brand AI content, voice rules, templates, glossary.

Encrypted environment variable vault with AI access policies, keeping secrets safe from AI agents.

Give AI agents access to form submissions — read, search, update, and process file attachments.

Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.

MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.

Vehicle data for AI: VIN decoder, automotive specs, stolen checks, valuation and way more.

AI Constraint Engine — enforces CLAUDE.md and .cursorrules as laws. 51 MCP tools.

Multi-session browser MCP — 15 parallel isolated browsers, 37 tools, stealth, self-improvement.

Local task scheduler and worker manager with MCP integration for Claude Desktop.

Google Analytics 4 MCP: reports, realtime data, custom dimensions, data streams.

Google Search Console MCP: search analytics, URL inspection, site management.

Google Ads MCP with MCC support: 35 tools for campaigns, keywords, reporting, GAQL.

Let AI agents create configurable voice agents via meeting rooms and return structured data.

First-party Provenote MCP server for drafts, research threads, auditable runs, and knowledge search.

Compare-first local MCP sidecar for browser AI workflows.

AI-powered biblical research tools — lexicons, morphology, manuscripts, and more.

HREVN trust layer for baseline diagnostics and verifiable workflow integrity for AI agents.

Burn-after-read encrypted notes. E2E encrypted, decentralised on the Internet Computer.

Peru vehicle auction catalog and AVT market valuations for VMC Subastas

Zero-Knowledge Context™ & Neural Handover™ for AI Agents. The Trust Layer for AI Memory.

Find novel, statistically validated patterns in tabular data — hypothesis-free.

Real-time collaborative coding via MCP — two developers, one codebase

SSH Linux metrics, baselines, anomaly detection, and plain-English infrastructure explanations.

Explore, analyze, and decompile Java JAR files via MCP

Record debug sessions, commands, failed attempts, and successful fixes in local SQLite storage.

News MCP: real-time headlines & custom news search across 7 regions. Free, just sign in with Google.

Aggregate multiple MCP backends behind a single stdio endpoint with namespaced routing.

Search Black-owned businesses in South Florida by category, neighborhood, or need.

OAuth 2.0 for AI agents — scoped delegation tokens, audit trails, and revocation.

Manage Google Ads, Meta Ads, and LinkedIn Ads through AI. 200+ tools, full read and write.

Scan dependencies for license compliance — copyleft conflicts, unknown licenses, risk.

YouTube as a queryable database for AI agents. 41 tools, zero config.

Provenance and governance layer for AI-readable knowledge. NodeRail answers what AI should trust.

qcqx-project-manage MCP Server — 将项目管理能力暴露给 AI Agent（Cursor、Claude Desktop 等）

MCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.

Privacy-first work tracking with summaries, reports, coaching, and AI-ready long-term memory.