muninn
v2.3.7
io.clawhub.endgegnerbert-tech/muninn
面向 AI Agent 的通用上下文协议(CXP)。v2.3.7 内置最新的高性能 CXP 引擎(2026-02-13 编译),修复记忆失忆问题,支持 macOS 二进制与 pfeilschnell 索引。由 @Blackknight1dev 创建。
“Commerce Engine” 共 889 个结果
v2.3.7
io.clawhub.endgegnerbert-tech/muninn
面向 AI Agent 的通用上下文协议(CXP)。v2.3.7 内置最新的高性能 CXP 引擎(2026-02-13 编译),修复记忆失忆问题,支持 macOS 二进制与 pfeilschnell 索引。由 @Blackknight1dev 创建。
v1.0.0
io.clawhub.artyomx33/geo-optimizer
为 AI 引用优化内容(GEO)。当用户提及 GEO、生成式引擎优化、AI 引用、被 AI 引用或为 ChatGPT/Claude/Perplexity 可见性创建内容时使用。
v2.0.0
io.clawhub.agisearch/excel-pro
电子表格操作者。不是教程,而是诊断引擎。识别最佳路径——公式、数据透视表、清洗工作流或 VBA——并交付可靠结果。
v2.0.0
io.clawhub.agisearch/game
面向 AI 智能体的即时游戏设计引擎。一句话描述任意游戏概念,即可得到完整可玩的设计。棋盘游戏、卡牌游戏、休闲游戏等类型皆可。
io.smithery.vdineshk.dominion-observatory
Behavioral trust scoring and MCP gateway proxy for 14,820+ MCP servers. Query real attestation data — interaction history, success rates, latency, uptime — before your agent executes sensitive operations. **8 tools** for trust evaluation, server discovery, and health monitoring: - `get-trust-score` — instant trust score (0-100) for any MCP server - `query-server` — full behavioral profile with attestation evidence - `list-servers` — browse the entire 14,820+ server directory - `get-leaderboard` — top-ranked servers by trust score - `check-health` — real-time uptime and latency checks - `get-compliance-report` — MiCA Article 12 compliance attestation receipts - `report-outcome` — report tool call outcomes to improve trust data - `get-baselines` — historical behavioral baselines **MCP Gateway Proxy**: Route agent calls through Observatory for automatic trust verification and compliance attestation. Every proxied call gets a trust check + signed attestation receipt. **Use cases**: Agent-to-agent commerce trus
v1.0.0
io.clawhub.ypw757/bocha-skill
使用博查 AI 搜索 API(Bocha AI Search)搜索网页——面向中文内容优化的搜索引擎,需要 BOCHA_API_KEY,支持网页、图片与新闻搜索及高质量摘要。
io.smithery.axel-belfort.user-agent-parser
面向 AI 智能体的 user agent 字符串解析 API。将任意 user agent 解析为结构化数据:浏览器(名称、版本)、操作系统(名称、版本)、设备类型(桌面/移动/平板)、渲染引擎与机器人识别。工具:utility_parse_user_agent。适用于分析数据处理、爬虫与机器人识别、设备定向或浏览器兼容性检查。返回:{browser, os, device, engine, isBot}。无需 API 密钥——在 Base L2 上以 x402 微支付 $0.001/次。
io.smithery.axel-belfort.text-to-speech
面向 AI 智能体的文字转语音 API。基于 Google TTS 引擎把文本合成为 20 多种语言的自然语音,返回可直接播放的 base64 编码 MP3。工具:media_text_to_speech。适用于语音通知、无障碍功能、音频内容生成或构建语音交互界面。返回:{audio(base64 MP3), language, duration}。无需 API 密钥——在 Base L2 上以 x402 微支付 $0.005/次。
v1.0.1
io.clawhub.chenchaoqun/a-stock-premarket-briefing
A 股盘前简报技能,交易日开盘前分析市场新闻、宏观事件,生成投资参考报告。整合 multi-search-engine 和 summarize,无需 API Key。
io.smithery.augiemazza.varrd
VARRD is the Cursor for trading — an AI-native quant research engine that turns domain knowledge into statistically validated trading edges. Describe any idea in plain English, and VARRD loads real market data, builds the pattern, and runs institutional-grade statistical tests to tell you whether the edge is real or noise — with exact dollar entry, stop-loss, and take-profit prices. Most AI trading tools skip the hard part. They’ll run a backtest and tell you what you want to hear. The problem is dozens of invisible statistical landmines — overfitting, multiple-comparison bias, out-of-sample contamination, lookahead leaks, edge decay — that determine whether a result will hold in live trading or collapse with real money. VARRD enforces these corrections at the infrastructure level. The AI cannot skip them. VARRD isn’t just a testing engine. Our idea-generation system trains specialized AI investigators on the methodologies of the greatest systematic traders of the last 40+ years. They generate institutional
io.smithery.anysearch-ai.anysearch
面向 AI 智能体的统一实时搜索引擎技能。
io.smithery.mcp-dir.olist-mcp
# Olist Tiny ERP Olist Tiny(原 Tiny ERP)电商 ERP,完整接入官方 v3 REST API:商品、库存、订单、电子发票(NF-e/NFC-e)、应付与应收账款、联系人、发货、采购与服务订单、CRM 和价格表。支持查询与操作。可与 Banco MCP 配对,对银行流水与 ERP 做对账。你在自己的 Olist 账号中创建应用并通过 OAuth 授权。 适用于任何 MCP 客户端。远程服务器:`https://api.mcp.ai/p_olist`
io.smithery.shokjak.travel-deals-mcp
Travel Deals MCP 是一个 Model Context Protocol 服务器,让 AI 智能体实时搜索精选度假套餐、度假捆绑和旅行优惠——无需网站、无需 SEO、无需搜索引擎。
v0.7.2
io.github.fetchsandbox/mcp
面向 agent 的确定性验证引擎:为修复提供证明——旧代码上失败、新代码上通过。
v0.7.1
io.github.keyline-dev/keyline
Design engine for AI agents: images and video at every size, no Chrome needed
v1.42.0
app.sallim/contract-compass
韩国公共采购法规:规则引擎裁定、法条检索与实时法院判例。
v0.9.1
io.github.autokeren/ghostfox
Self-hosted stealth browser for AI agents: Firefox engine + Rust MCP runtime.
v1.4.1
io.github.RagingOrangutan/rootvine-mcp
为 AI 智能体提供覆盖 15+ 平台的音乐与游戏跨平台解析。
v0.2.2
io.github.awv-informatik/classcad
Build and verify CAD parts and assemblies with the ClassCAD engine, locally, no server needed.
v0.1.0
dev.opx-status/opx
Buyer-side machine commerce: choose where to spend using recent paid x402 provider evidence.
v1.0.0
ai.marketbrew/marketbrew
Read-only Market Brew search engine modeling and AI visibility data via OAuth.
v0.89.0
io.github.cmssy-io/cmssy-mcp
Headless CMS whose page sections are defined by your own code: pages, records, media, commerce.
v0.6.7
io.github.emergent-wisdom/meaning-model
Revisable general-purpose models with opt-in story and ideation add-ons. Rust engine required.
v0.1.17
dev.tabnas/mcp
基于 tabnas 解析引擎的七个工具:解析、校验、诊断、测试数据与结果对比。