SAGE 求解引擎
v0.1.1
io.github.pragnakar/sage-solver-mcp
LLM 原生的优化求解器:通过 HiGHS/OR-Tools 实现 LP、MIP、投资组合与排程。
“Rag” 共 303 个结果
v0.1.1
io.github.pragnakar/sage-solver-mcp
LLM 原生的优化求解器:通过 HiGHS/OR-Tools 实现 LP、MIP、投资组合与排程。
v0.2.0
io.github.garagon/aguara-mcp
面向 AI agent 技能与 MCP server 的安全扫描器。
v2.9.0
com.apple-rag/mcp-server
面向 MCP 客户端的 Apple 开发者文档检索,支持语义搜索、RAG 与 AI 重排序
v0.3.4
io.github.indragiek/uniprof
为人类与 AI 智能体设计的通用 CPU 性能剖析器。
io.smithery.axel-belfort.web-scraper
Web content extraction API for AI agents. Scrape any URL and get clean, structured Markdown content with navigation, ads, and scripts stripped. Full JavaScript rendering via headless Chromium. Single and batch (10 URLs) modes. Built for RAG pipelines and AI research. Tools: web_scrape_to_markdown (single), web_scrape_batch (up to 10 URLs). Use this for RAG ingestion, research, content analysis, data extraction, or competitive intelligence. IMPORTANT: For screenshots/PDFs of pages, use capture_screenshot instead. For SEO analysis, use seo_audit_page. Returns: {markdown, title, wordCount, links[]}. No API key required — x402 micropayment $0.005/call on Base L2.
io.smithery.axel-belfort.vector-search
面向 AI 智能体的内存向量检索 API。存储文档并按语义查询,采用 TF-IDF 向量化与余弦相似度,是 Pinecone/Weaviate 的轻量替代,适合小数据集。工具:data_vector_search。适用于构建简单 RAG 系统、文档匹配或小规模集合(少于 1 万篇)的语义检索。注意:全网搜索请改用 web_search_query。返回:{results[], scores[], matchCount}。无需 API 密钥——在 Base L2 上以 x402 微支付 $0.005/次。
io.smithery.beforeyouship.cost-model
**在动手开发之前**就为 LLM 应用建模真实的月度成本。不是简单的 token 计算器:它把重试、提示缓存、批处理折扣、基础设施开销以及 3×/10× 增长都纳入模型,覆盖 GPT-5.x、Claude、Gemini、DeepSeek 等。 **无需 key 也能用。**连接后即可提问——演示模式覆盖六个免费档模型。Pro API key([beforeyouship.dev](https://beforeyouship.dev))解锁全部 18 个模型目录。 ## 工具 | 工具 | 作用 | |---|---| - **`estimate_cost`** 针对给定用量下的架构做完整成本建模。返回各模型的 Naive / Realistic / Worst Case 月度美元成本、增长情景和带倾向性的建议。 | - **`get_model_prices`** 当前每 100 万 token 定价(输入、输出、缓存、批处理),含上下文窗口与数据时效元信息。 | - **`list_archetypes`** 七种预设架构模式(聊天机器人、RAG 流程、多步智能体等),可作为估算起点。
v0.2.14
io.github.heubme2020/datasinking
Full-text financial reports (US, China, Japan, Korea, Taiwan) as clean Markdown for RAG agents.
v3.5.0
io.github.jztan/pdf-mcp
针对单个 PDF 或整个文件夹的智能体 RAG:混合检索、按需读取页面、表格解析与 OCR。
v1.0.0
io.github.saulius876-lgtm/youtube-transcripts
Bulk YouTube transcripts from videos, channels, playlists or search: text, RAG chunks, SRT, VTT.
v0.2.2
io.github.4hmetuyar/prompt-injection-scanner
Scans RAG content/scraped pages for indirect prompt injection
v1.0.1
dev.workers.cybermax-tools.cybermax/leafmelt
PDF/Word/Excel/HTML to clean Markdown for LLMs and RAG. Keys $19/mo; 50 free calls a day.
v1.0.2
io.github.industrial-platform-ai/pdf-text
x402 PDF text, pages, and metadata for AI/RAG. $0.0015 per successful PDF.
v1.0.2
io.github.industrial-platform-ai/article-extractor
x402 clean article text and metadata for AI/RAG. $0.002 per successful article.
v1.0.0
ai.divinci/divinci
Release management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs
v1.0.13
io.github.CSOAI-ORG/agent-prompt-injection-firewall-mcp
智能体的 WAF。
v0.4.5
io.github.BigCactusLabs/dead-letter
把 .eml 邮件导出转换为整洁 Markdown,用于 RAG、LLM 流水线与本地知识库。
v0.1.1
io.github.4hmetuyar/vector-store-scanner
Probes vector-database endpoints for unauthenticated exposure of embeddings/RAG data
v0.1.4
com.cnrcode/tillpad
为远程 MCP 上的代理任务提供有边界的键值持久化(KVP)、RAG 检索与数据擦除回执。
v1.0.0
com.penguindriver/glossary
AI 與科技名詞白話解釋:MCP、RAG、AI 代理人等名詞的白話定義。台灣繁體中文 MCP 工具。
v1.0.0
io.github.zhaoxinghua09-cell/medxpert-library-connector
Local RAG MCP server for your own .md knowledge base: BM25 + local Ollama, offline, zero egress.
v1.0.0
io.github.classofdoom/tresslers-intelligence
Sovereign intelligence dossiers, daily briefings, RAG search, knowledge graph, codon optimizer.
v1.0.0
io.github.lintlab/pdf-to-markdown
Convert PDF URLs to clean Markdown and text for RAG and LLM input. Pay per PDF on Apify.
v0.1.0
io.github.AsterMindAI/astermind-mcp
On-device reranking that cuts RAG context tokens ~67% while keeping a relevant passage.