MCP 工具广场｜Model Context Protocol 服务器目录

Demand-side commerce for AI agents. Tell iwant.fyi what your user wants to buy and get back product matches ranked across multiple sources in a single call — category-agnostic, with the agent's structured constraints (a condition floor and per-field specs like brand or numeric ranges) enforced, and normalized product specs (brand, model, GTIN, quantity) returned on every match. Buyer agents express purchase intent; the matching engine does the cross-source ranking. MCP-native with an HTTP and A2A interface. Reference implementation of the open iwant.fyi demand-side protocol v1.0.

DevMatch is an MCP server for hiring engineers based on what they've actually built. Connect from Cursor, Claude Desktop, or any MCP-compatible AI assistant and search 35M+ developers ranked by verified open-source contributions — not LinkedIn keywords or self-reported skills. **Three tools:** **`find_candidates`** — paste a job description, get a ranked shortlist with bio, top repos, contribution evidence, and contact info. Pro tier adds verified email enrichment on the top 5 results. **`get_profile`** — deep-dive any GitHub handle. Bio, recent activity, top projects, and outreach channels in one call. **`find_similar_projects`** — landscape mapping from a seed repo with top contributors surfaced, so you can pivot from a project to its maintainers in one step. Built for mission-driven teams that want engineers who care about the work, not just check the keyword box. OAuth sign-in (no AP

Prediction market event resolution API for AI agents. Determine if real-world events occurred with confidence scores. Aggregates news, price feeds, and web data for binary, numeric, and categorical outcomes. Settlement oracle for prediction markets. Tools: event_resolve_outcome, event_verify_claim, event_check_price_threshold. Use this for resolving prediction market bets, verifying event outcomes, or building automated settlement systems. IMPORTANT: For market odds and probabilities, use prediction_list_markets instead. Returns: {resolved, outcome, confidence, sources[]}. No API key required — x402 micropayment $0.005/call on Base L2.

ResultRail by LarryBuildsAI sells pay-per-success public-data result packs for AI agents. It returns source URLs, confidence, timestamps, and receipt hashes for domain enrichment, URL extraction, and single-result lookup workflows. Use it when an agent needs one useful public-data result with a clear stop condition.

A fully managed remote MCP server that provides up-to-date documentation, code samples, knowledge about the regional availability of AWS APIs and CloudFormation resources, and other official AWS content.

Manage and explore forum communities by searching topics, reading posts, and viewing user profiles. Facilitate communication through chat channels, draft management, and categorized content discovery. Streamline interactions with tools for filtering topics and generating post summaries or replies.

SEO keyword research API for AI agents. Generate keyword ideas from Google Suggest with search intent classification (informational/transactional/navigational), long-tail variations, related queries, and content planning data. Tools: seo_research_keywords. Use this for content strategy, blog post planning, PPC keyword discovery, or competitive keyword analysis. IMPORTANT: For on-page SEO audit, use seo_audit_page instead. Returns: {keywords[], intent, volume, relatedQueries[]}. No API key required — x402 micropayment $0.01/call on Base L2.

Cap Rate Signals — US Real Estate Investment Intelligence Identifies US real estate markets that are about to reprice upward, before consensus catches up. Tracks confirmed corporate investment — semiconductor fabs, pharma plants, defense campuses, data centers — and scores markets based on where workers are arriving but housing demand hasn't yet been priced in. 14 tools covering market discovery, investment briefs, head-to-head comparisons, regional comps, signal alerts, and map data. Data sourced live from a proprietary database monitoring 109 companies across 40+ US metros. Use it to ask: Where should I invest right now? What's happening in Indianapolis? Show me semiconductor markets under $300K. What moved this week?

Access the OpenAlex academic research catalog — 270M+ publications.

Free, keyless MCP server with 50 read-only blockchain tools for Bitcoin, Ethereum, and Mezo. No installation, no API key required - just add the URL to your MCP client and start querying balances, transactions, blocks, ENS names, ERC-20 tokens, smart contracts, and more. Runs on Cloudflare's global edge network via Streamable HTTP. All tools are strictly read-only and stateless.

The cultural GPS for AI commerce. 504,472 aesthetic worlds mapped across 193 dimensions — from dark academia to k-beauty to quiet luxury. 3,154 autonomous agents update intelligence every 48 hours. 9 tools: product recommendations with affiliate links, brand cultural position, trend intelligence, commerce gap predictions, world comparisons, and live cultural signals. Free. Open source. MIT licensed. 14 AI companies already consume our data at 33,000+ requests/hour. Open Source Commerce For All.

Search Wikipedia, read summaries and full text, target sections, find nearby pages, list languages.

Automate tax workflow tasks and manage client engagements. Track deadlines, organize documents, and handle billing for accounting firms.

Search Google News for current and recent articles. No API key required. Data via SerpAPI; Smithery is not affiliated with Google.

Secureship MCP gives AI assistants access to a multi-carrier shipping API covering rate comparison, label generation, package tracking, pickup scheduling, address book management, shipment history, customs documents, and more — across carriers like UPS, FedEx, Purolator, Canpar, and others. Browse 150+ live endpoint schemas, parameters, and auth details — always current, never stale. Secureship isn't just for shipping with one carrier — it's a multi-carrier shipping platform, and this MCP server gives AI assistants full access to the API documentation for every supported action: compare rates across carriers, generate shipping labels, track packages, schedule pickups, manage address books, review shipment history, produce customs documents, handle invoices, and even perform actions available on the Secureship web dashboard — all through a single API. The MCP documentation server exposes

Magic: The Gathering card search, combo lookup, draft analytics, and Commander tools.

Discover supported verification scopes and the claims they provide. Initiate and monitor data wallet verification flows to securely receive redacted wallet data. Clean up completed sessions to keep workflows organized.

Hyperliquid perpetual market data API for AI agents. Real-time order books, mid prices, funding rates, open interest, 24h volume, and OHLCV candles for all 229 perp markets on Hyperliquid L1. Direct on-chain data, no CoinGecko dependency. Tools: hyperliquid_get_market_data (single), hyperliquid_get_all_markets (overview), hyperliquid_get_candles (OHLCV). Use this for trading signals, market analysis, backtesting, or building Hyperliquid trading bots. The foundational data layer for any Hyperliquid integration. IMPORTANT: For whale tracking, use hyperliquid_track_whale_positions instead. Returns real-time L1 data. No API key required — x402 micropayment $0.001/call on Base L2.

**Memxus** is multi-platform persistent memory for AI assistants. Save project context, preferences, and decisions once — recall them in Claude, ChatGPT, Cursor, and other MCP clients. ## What it does - **Remember** — store facts, preferences, and project context with collections and tags - **Recall** — semantic search across your memories - **Get context** — formatted context blocks for the current topic - **Manage** — list, inspect, update scope, and delete memories ## Connect - **OAuth** (recommended): sign in with Google via your Memxus dashboard - **API key**: create an `aimem_*` key at [dashboard.memxus.com](https://dashboard.memxus.com) **MCP endpoint:** `https://mcp.memxus.com/mcp` **Docs:** [memxus.com/docs/mcp](https://www.memxus.com/docs/mcp) **Install:** [memxus.com/install](https://www.memxus.com/install) **Privacy:** [memxus.com/privacy](https://www.memxus.com/privacy) ## T

Marine, maritime, nautical and sailing data for AI assistants and chatbots. Mediterranean marine forecast: wind, wave, swell, gust. Tide tables and tidal predictions. Sea routing and passage planning on a coastline-aware maritime graph. Curated POIs: marinas, ports, harbors, anchorages, moorings, fuel. Real data, cited sources, never invented.

Discover personalized Four Pillars (Saju) readings, from daily to yearly fortunes and 10-year luck cycles, based on your birth data. Check relationship compatibility and receive Yongshin-driven guidance with practical tips on colors, directions, and careers. Convert between lunar and solar calendars and tailor interpretations across different schools.

Enable your LLMs to perform accurate numerical calculations with a simple API. Leverage basic arithmetic and statistical functions to enhance your applications. Simplify complex mathematical tasks effortlessly and improve your model's capabilities.

Connect your AI agents to GitHub — manage repos, issues, PRs, workflows, and more

**Your company's brain for AI agents.** Quelvio continuously understands your organization's knowledge across every connected system — what's authoritative, what's recent, what's persistent, what's temporary, and what should be forgotten. Returns cited answers grounded in your authoritative sources, refusing when the corpus doesn't actually answer the question. ## What makes Quelvio different - **Cross-document supersession** — when sources conflict, surfaces the current truth and explicitly names what it supersedes - **Authority-weighted retrieval** — weights documents by who said them on the relevant topic - **Refuses on weak context** — when the corpus doesn't actually answer, says so. No hallucinated numbers, no fabricated citations - **Cross-source synthesis** — reasons across Slack, Confluence, Notion, Drive simultaneously with explicit source attribution - **Lifecycle awareness**