com.anots由 anots.com 發布官方發布者v1.0.0更新於 Oct 24, 2026
Discover and query every business on ANOTS — search, ask, or find-and-ask over MCP.
遠端 ANOTS 目錄伺服器，讓助理依需求尋找商家、向其 AI 代理提問，並並排比較各家回答。
Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。
把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。
閱讀 https://sourceweft.com/mcp/com.anots%2Fdirectory/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。把它新增到你客戶端的 mcpServers 設定中。
{
"mcpServers": {
"directory": {
"type": "http",
"url": "https://api.anots.com/mcp"
}
}
}Resilient 4-Layer Memory Architecture for TCAM v1.4 (Triadic Cognitive Augmentation Model)
The TCAM Memory System implements a fault-tolerant memory architecture where each layer operates independently, ensuring that system failures in one layer do not cascade to others. Memory operations are handled by a dedicated Memory Service running on Qwen 3.5 9B (local LLM).
Dedicated process running on Qwen 3.5 9B for:
The Terminal UI dashboard (anots dashboard) provides:
Import large conversation files into the ANOTS memory system:
See data/import/README.md for detailed documentation and examples.
See .kiro/specs/memory-system/ for complete specification:
requirements.md - Functional requirementsdesign.md - Technical designtasks.md - Implementation tasksMIT
來源：README.md，提交 e43bf63
Search the ANOTS directory for businesses whose AI agent can answer a question or need. Returns matching businesses with their slug, name, what they do, and agent-card URL. Use this first to discover which agents to ask.
limitquery必填Ask a specific business's ANOTS agent a question, by slug. The agent answers from that business's own knowledge base and tools (live data, not scraped HTML). Get the slug from search_businesses.
slug必填question必填Discover the most relevant ANOTS businesses for a need AND ask each one in a single step, returning their answers side by side. The fastest way to answer a purchase-intent or research question across the directory.
limitquery必填已滿足適用檢查項的 90%
該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。
請在儲存庫或註冊中心條目中宣告授權條款。
.├── src/ # Source code├── tests/ # Test files├── data/ # Chronicle storage├── codex/ # Agent Codex (L4)├── docs/ # Documentation└── .kiro/specs/ # Specification documents# Install dependenciesnpm install --legacy-peer-deps
# Pull Qwen 3.5 9B modelollama pull qwen2.5:9b-instruct-q4_K_M
# Pull embedding modelollama pull nomic-embed-text
# Start Qdrant (using setup script)# Windows PowerShell:.\scripts\setup-qdrant.ps1
# Linux/Mac:bash scripts/setup-qdrant.sh
# Or manually with Docker:docker run -d --name qdrant -p 6333:6333 -p 6334:6334 -v qdrant_storage:/qdrant/storage qdrant/qdrant
# Start Redisdocker run -d --name redis -p 6379:6379 redis
# Build and install globallynpm run buildnpm install -g . --legacy-peer-deps# Interactive main menuanots
# Real-time monitoring dashboard (Terminal UI)anots dashboard
# Chat with Axiom (TCAM Node C)anots axiom
# Start MCP server (19 tools for IDE integration)anots mcp:start
# Start REST API serveranots api:start
# Start API with Axiom chat endpointanots api:start --axiom
# Search memoryanots memory:search "your query"
# Import conversation (JSON/Markdown)anots import conversation.json --type general
# System statusanots status
# Configuration wizardanots setup
# Show all commandsanots --help# Check Qdrantcurl http://localhost:6333/health
# Check Redisredis-cli ping
# Check Ollamaollama list# Buildnpm run build
# Run testsnpm test
# Run tests with coveragenpm run test:coverage
# Lintnpm run lint
# Format codenpm run format# Import Ubik conversationnpm run import -- data/import/conversation.json --type ubik
# Import Axiom conversationnpm run import -- data/import/conversation.md --type axiom
# Preview import without writing (dry run)npm run import -- data/import/conversation.json --dry-run
# Custom chunk size (messages per chapter)npm run import -- data/import/large-file.json --type ubik --chunk-size 100