Awesome MCP Servers

Discover, extract, and interact with the web - one interface powering automated access across the public internet.

Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more

Monetize your AI agent with contextual product recommendations

Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.

Give Claude native access to the Match It Up professional networking platform. Browse members, send DMs, post signals, manage bonds, and more — 25 tools, zero per-tool authentication.

Local-first, full-text code search MCP server for AI coding agents. Indexes your codebase with trigram-based indexing for sub-100ms queries. Agents can search across 10k+ files, filter by language or symbol kind, and get structured JSON results — all offline, no API key required

VoidLang - LLM Native Machine Code MCP

Unified API for AI agents to deploy cloud infrastructure across AWS, Azure, and GCP autonomously

多对象协作技术方案编排引擎。三个 AI Agent 并行提案、交叉审查、可行性收束，投票输出 Top 3 方案

A local-first, LLM-agnostic memory layer for AI assistants

SocialDataX（社媒数据助手）is a read-only MCP for 小红书 / Xiaohongshu / XHS / RedNote, supporting 笔记搜索, 笔记详情, 评论, 评论回复, 博主信息, 博主笔记列表, note search, note details, comments, comment replies, creator profiles, and creator notes.

Run raw FFmpeg commands on our infrastructure via MCP.

Local codebase context compiler for AI coding agents, turning TypeScript/Node workspaces into compact, verifiable context packs.

Full Mailchimp control from Claude - 53 tools for audiences, campaigns, automations and more.

A headless terminal and tmux interaction server for Model Context Protocol.

Transparent MCP proxy with OpenTelemetry tracing. Wrap any MCP server, persist traces to any OTel backend · SQLite · Postgres · MySQL. No code changes needed.

Connect with the authenticated external API, or use the MCP transport for agents.

faist mirrors your Fastmail inbox into your own Supabase, then exposes it to Claude and other MCP clients as SQL. With hybrid lexical and semantic search.

Official MCP server for Very Good FFmpeg

Persistent project context for AI coding agents: captures decisions, rationale, and rejected paths so agents stay consistent across Claude, Cursor, Codex, and any MCP enabled platform.

Search 6,500+ curated AI apps from the HyperStore directory via 8 MCP tools.

Self-hosted MCP server for Obsidian: semantic + full-text search, wikilink graph, note CRUD, OAuth, and a self-describing vault guide.

Connect AI assistants to Xitoring monitoring: servers, uptime, incidents, metrics, SSL, and alerts

AI intelligence oracle + cross-border settlement rail. 10-layer Stability Oracle (climate, macro, FX, ESG) with x402 pay-per-call API. USDC/EURC settlement on Base at 1.385% all-in.

Send and receive transactional email through Nuntly, a developer-first email platform with EU data hosting. Tools covering emails, domains, webhooks, inboxes, and threads.

Curated, ranked directory of community-built plugins for Claude Code and OpenAI Codex (includes MCP servers).

MCP server for Apollo.io, search leads, enrich contacts, manage sequences & CRM from Claude Code, Cursor, or any MCP client. 45+ tool calls covering the full Apollo.io API.

x402 provider rankings + Ed25519-signed payment receipts + signature verification (3 tools).

Skill for AI Agents : wrapper to generate video for local wan2GP instance

Brazilian Open Finance MCP — connect 30+ banks (Itaú, Nubank, Bradesco, Santander, Inter, BB, Caixa, C6 and more) to Claude/Cursor. 13 read-only tools.

Stubble learns how you work and organizes your day automatically. Export timesheets, surface insights, and supercharge your AI tools.

AI-native MCP server connecting Claude, Cursor, Windsurf, and other AI assistants to TestRail — manage test cases, runs, and results through natural-language conversation, with typed schemas built for LLMs.

Strict AI code reviewer powered by Groq. Finds bugs, SQL injections, hardcoded secrets and vulnerabilities. Scores code 0–100 with concrete fixes.