国内 MCP 服务推荐（飞书 / 高德 / 12306）

Hosted MCP for e-commerce: live product catalog, stock, and pricing for AI agents.

Vet LLM-emitted shell commands BEFORE execution. 26 destructive-pattern rules / 8 families.

Brand-intelligence MCP: momentum scoring, signal evidence, and competitive context for agents.

MCP server for wheelfor.com — create, spin, and manage decision wheels

Turn an IDF domain into an MCP server with invariants and role scopes in every tool description.

Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.

Compare, estimate, and deploy cloud infrastructure across AWS, GCP, and Azure for AI agents.

Control CastHub digital signage. Manage TVs, presentations, schedules, and emergency alerts.

Social media analytics, post insights, and competitor benchmarking for AI agents.

Manage restaurant bookings via Claude — read covers, find guests, move tables, send wedding quotes.

Rust MCP server for binary analysis and reverse engineering.

Lets AI clients search, explore, query, and visualize data in a Metabase instance.

Code intelligence MCP server — impact analysis, semantic search, dependency graphs

Trust infrastructure for AI agents. Portable reputation (JTS 0-5), agent discovery, vouching.

An MCP server that provides [describe what your server does]

Store, retrieve, and pin encrypted files on IPFS via MCP tools for AI agents and workflows

AI runtime upgrade safety + provider-side regression detection (snapshot diff + fingerprint).

AI agent token-cost telemetry + 429 prediction. Per-agent attribution, anomaly + routing + quota.

MCP server for OpenClaw deployment health: gateway, resources, errors, skills, upgrades, disk.

Vet third-party AI agent extensions + agent-config files (AGENTS.md, .cursor/rules, CLAUDE.md).

Korean crypto × AI media MCP — channel stance, daily briefs, RAG, canonical store, AI personas.

An MCP server that through www.gdacs.org provides access to web‐based disaster information systems.

The firewall for MCP tool calls. Block, audit, replay with evidence bundles.

Mistral AI MCP server: chat, OCR, Voxtral audio, Codestral FIM, vision, agents, batch.

Your clipboard, but Claude can read it. Type-classified, secret-encrypted. macOS + Linux.

MCP servers for Indian APIs including stocks, GST, railways, banking, and RTO.

MCP server for Indian banking: IFSC lookup, UPI VPA validation, bank UPI status.

Agent orchestration platform - multi-agent spawning, tickets, boards, and workflows

Current US rental market data for AI agents: 1,500+ submarkets, monthly rent + vacancy + trends.

Ephemeral 7-day hybrid vector+BM25 working memory, multilingual, backed by Redis Stack.

327 dev tools via REST API and MCP. Generate Dockerfiles, schemas, K8s, APIs, and more.

Package intelligence MCP for AI agents — 22 tools, 19 ecosystems, AGPL SDK, free.

Pull churn from Stripe, Postgres, MySQL, or pasted feedback. AI-ranked drivers + fixes.

Multi-tenant business platform — 6,000+ RBAC-gated MCP tools across finance, ops, docs, agents.

Publish to Bluesky, Threads, LinkedIn, Facebook Pages, and Instagram from ChatGPT or Claude.

Recall, check, search, timeline, and graph tools for fiction writers via Seizn Memory v3.

Open-source MCP server connecting Claude to Filevine practice management. Built by Oktopeak.

Self-custodial crypto + DeFi MCP for AI agents. Ledger-signed. EVM, TRON, Solana, BTC, LTC.

Hosted MCP server for Fortnox. Connect Claude, ChatGPT, Cursor to live Fortnox via OAuth.

Manage SRG+ hubs, channels, content, assets, users, and workspaces from any MCP-aware AI agent.

VantaGate MCP Server & OpenAPI integration - Human-in-the-Loop for AI Agents

Engineering log of self-hosted AI on NVIDIA DGX Spark (GB10/SM121A). 60+ articles indexed.

MCP server for Base L2 DeFi operations with 9 monetized endpoints

Publish HTML, Markdown, KV, JSON, and files to brewpage.app from AI assistants. No signup.

AI agent security via MCP: C3 firewall, C4 immune system, C5 action guard, self-evolving prompts.

Accessibility compliance for AI coding tools. WCAG 2.2 reviews with shared evidence.