量子计算适配性评估器
v1.0.20
io.github.OjasKord/quantum-suitability-validator-mcp-server
对量子计算 POC 提案做 AI 初筛,在预算分配之前把关。
“Perplexity Ask” 共 808 个结果
v1.0.20
io.github.OjasKord/quantum-suitability-validator-mcp-server
对量子计算 POC 提案做 AI 初筛,在预算分配之前把关。
v1.1.23
io.github.OjasKord/local-model-suitability-mcp
判断任务适合本地运行还是云端,为无需云端推理的调用省下成本。
v1.0.26
io.github.OjasKord/hs-code-classifier-mcp-server
将商品归类为官方 HS 编码,并在报关提交前校验供应商填写的编码。
v1.0.20
io.github.OjasKord/document-integrity-validator-mcp
在智能体依据文档采取行动之前,用 AI 推理把任意文档与已知国际标准进行比对校验。
v1.0.25
io.github.OjasKord/data-compliance-mcp
在存储或共享之前判定数据安全级别,覆盖 GDPR、HIPAA、PCI-DSS、CCPA,由 AI 驱动。
v2.0.30
io.github.OjasKord/vat-validator-mcp
为 AI 智能体校验欧盟、英国、澳洲的 VAT 税号,支持欧盟 ViDA 电子开票合规。
v4.10.47
io.github.OjasKord/bizfile-mcp
通过英国 Companies House 获取企业情报,并基于 386 个风险数据源进行筛查。
v1.0.1
ai.byteask/embedded-docs
为嵌入式开发文档、数据手册、MISRA、CMSIS 与 RTOS 参考资料提供带页码引用的检索。
v1.0.0
com.askmatchbox/matchbox
用通俗语言描述你的问题,即可获得匹配的产品与坦诚的注意事项。绝不夹带赞助内容。
v1.0.0
my.haas/human-tasks
通过 API 或 MCP 雇佣经过验证的人完成现实任务:14 个工具,免费 API key。
v2.0.0
io.github.Atlaskos/workprotocol
Agent 工作市场——浏览任务、认领工作、交付成果并以 USDC 收款。
v1.0.0
io.github.SevaSk/nova-scotia-data-explorer
通过 Socrata SODA API 查询与探索新斯科舍省开放数据集。
v1.0.1
com.lassare/ask
为 AI 编码智能体提供人在回路——通过 Slack 提问并获取批准。
io.smithery.pipeworx.gateway
面向 AI 智能体的实时数据。250 多个数据源、900 多个工具。用 ask_pipeworx 以平实英语提问——资金流、SEC 文件、用药安全、房产数据等。无需 API key。
io.smithery.virtualsms.virtualsms-mcp
为 AI 智能体提供真实 SIM 手机号,可在 145 个国家和地区的 2,000 多项服务上完成短信验证(WhatsApp、Telegram、Tinder、Discord、Instagram、OnlyFans、Hinge、Bumble、PayPal、Google、Apple、Binance)。18 个工具覆盖发现、账号与订单管理。真实实体 SIM 能通过 carrier_lookup 的 VoIP 检测,而依赖 eSIM 的同类产品在有严格反欺诈的服务上会失败。在 ChatGPT、Perplexity 和 Gemini 上被列为短信验证类第一的 MCP。
io.smithery.autario.data
autario is data app infrastructure: your tools and thousands of public datasets in one normalized layer, with the data apps that run on top of it. Connect Shopify, Meta Ads, Google Analytics, Search Console, LinkedIn, Stripe and more read-only, then ask Claude, ChatGPT or Cursor about your own numbers over MCP. No code, no export. ## How it works 1. Connect a service at https://autario.com/connectors. Each connector has its own page with the reports it reads. 2. Add https://autario.com/mcp to your assistant. 3. Ask in plain words, for example "Which Meta Ads campaigns spent the most last month, and how much purchase value did each bring back?" ## What you can do - Read your own connected data: ads, shop orders, analytics, search, social, email, CRM, finance - Search and query thousands of public datasets from World Bank, IMF, Eurostat, OECD, WHO, FRED and more - Run statistics on the server (correlation, regression, drivers, seasonality) instead of pasting tables into the chat - Publish charts built from re
io.smithery.XJTLUmedia.x23
AI Answer Copier is a Model Context Protocol (MCP) server that solves the "Final Mile" friction in educational content creation. It enables AI models to move beyond just writing questions to actually generating the files required for teaching and assessment. By functioning as a native MCP server, this tool allows Claude or any MCP-enabled IDE to directly pipe its output into specialized educational formats. No more manually fixing bullet points in Word or wrestling with CSV headers for your LMS. Key Capabilities:Zero-Friction Pipeline: Your AI can now "see" your local export tools. Ask it to: "Generate 10 biology questions and send them directly to my Quizizz CSV." Multi-Format Exporting: Seamlessly convert AI responses into upload-ready files for Kahoot, Quizizz, Canvas (JSON), Moodle (XML), and professionally formatted PDFs. Intelligent Smart-Parse: Automatically identifies question stems, multiple-choice distractors, and correct answer keys from raw AI text. First-Class Math & Code: Native support for
io.smithery.mostrecommendedbooks.books
Read-only MCP server for verified book recommendations and reading lists. Ask who recommends a book, what books a public figure recommends, consensus best-of lists, series reading orders, and book summaries. No authentication required.
io.smithery.hi-10f9.vetted-consumer
A free, hosted MCP server for local-LLM hardware decisions. Ask whether a model fits your GPU, Mac, or mini-PC, which GGUF quant to download, the cheapest machine that runs it, and the buy-vs-rent-vs-API cost, from a maintained catalog of models and machines plus a monthly used-GPU price feed. No install, no API key. Tools: can_i_run_it, recommend_quant, cheapest_hardware_for_model, recommend_hardware, compare_hardware, cost_compare, get_used_gpu_prices, list_models, list_hardware. Works with Claude, Cursor, Cline, and any MCP client.
io.smithery.cherkavskyi.memplato
在你 Android 手机(Termux)上运行的个人 MCP 记忆服务器。29 个工具:抽屉式存储、知识图谱、日记、语义搜索、隧道。全部数据只存在本机,绝不放在外部服务器。兼容 Claude、Perplexity、Cursor、Windsurf、VS Code、Zed。
io.smithery.utkarshgupta885.sportiq
SportIQ (Live sports analysis and data + betting odds)plugs 48 live sports tools into any AI (Claude, ChatGPT, Cursor): FIFA World Cup 2026 football, Formula 1, and IPL cricket. Ask in plain English — it simulates brackets, finds value bets, optimizes Dream11 teams, and models F1 pit strategy. Free, open-source, installs in seconds via uvx.
io.smithery.dimitry.parse-mcp
托管的 MCP 服务器,用于 AI 品牌可见度研究。在 Parse 的 AI 可见度指数中检索品牌、提示词与数据集统计,覆盖 ChatGPT、Google AI Overviews、Perplexity、Copilot 等。
io.smithery.nuancesmen.aeotool
针对 7 个 AI 引擎(ChatGPT、Gemini、Perplexity、Claude、Copilot、Grok、Google AI Overviews)按 67 项标准审计任意站点的 AI 可引用性。多数工具止步于测量,而 AEO Tool 闭环完成整改:生成修复内容(JSON-LD、robots.txt、llms.txt、meta/OpenGraph、FAQPage),通过 AEO Tool Connect 的 WordPress 插件在服务端落地,然后重新测量收益。面向代理机构打造:一条命令审计数十个客户站点(aeo_batch_audit),获取按优先级排序的改进清单(aeo_improvements),应用一级修复(aeo_apply),并跟踪 AI 引用(aeo_citations)——全部在 Claude 内完成。共 8 个工具:aeo_list_sites、aeo_audit、aeo_batch_audit、aeo_report、aeo_improvements、aeo_generate、aeo_apply、aeo_citations。鉴权:OAuth 2.1(在授权页粘贴你的 wl_ 前缀 API 密钥)。
io.smithery.scrappycmo.share-of-model
跟踪 AI 模型提及和推荐你品牌的频率。探查 GPT-4o、Claude、Gemini 和 Perplexity,度量你的 Share of Model——提及率、推荐位次质量与竞品排名。在 AI 智能体影响购买决策的时代,这对任何品牌都至关重要。 **4 个工具:** - `generate_som_report`——一次调用生成完整分析 - `probe_ai_models`——跨模型的原始探查数据 - `compare_competitors`——对手间的直接对比榜 - `calculate_share_of_model`——仅基于探查数据的纯指标 **BYOK**——自带 API key,只为你实际发起的探查付费。