{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_mnmt4sjkrnsj","handle":"iflow-mcp-niksh06-rag-duckdb-with-mcp","url":"https://wellknown.network/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp","links":{"self":"https://wellknown.network/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp/record.json","html":"https://wellknown.network/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp","markdown":"https://wellknown.network/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp","status":"https://wellknown.network/api/v1/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp/status","claim":"https://wellknown.network/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-niksh06-rag-duckdb-with-mcp/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-niksh06-rag-duckdb-with-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_niksh06-rag-duckdb-with-mcp","summary":"MCP сервис для интеграции с Python RAG Server (DuckDB VSS)","description":"# MCP RAG Service\n\n**MCP сервис для интеграции с Python RAG Server (DuckDB VSS) v2.0**\n\nУлучшенный MCP сервис для работы с продвинутыми методами векторного поиска, основанный на принципе KISS (Keep It Simple, Stupid).\n\n## 🚀 Возможности\n\n### Основные функции:\n- **`rag_upload_file`** - Загрузка файлов в RAG сервер\n- **`rag_search`** - Продвинутый поиск по документам (гибридный, семантический, ключевой) с переранжированием и расширением запроса.\n- **`rag_get_file_content`** - Получение полного содержимого файла из базы данных.\n- **`rag_similar_documents`** - Поиск похожих документов\n- **`rag_analyze_collection`** - Анализ коллекции (кластеры, выбросы, центральность)\n- **`rag_get_collection_stats`** - Получение быстрой статистики по RAG коллекции.\n- **`rag_query_direct`** - Прямые SQL запросы к DuckDB VSS\n\n### Поддерживаемые форматы файлов:\n- Текстовые: `.txt`, `.md`\n- Документы: `.pdf`\n- Программный код: `.py`, `.js`, `.java`, `.c`, `.cpp`\n- Конфигурационные: `.json`, `.yaml`, `.yml`, `.ini`, `.toml`\n\n## 📋 Требования\n\n- Python 3.8+\n- Работающий Python RAG Server с DuckDB VSS\n- MCP совместимый клиент (например, Claude Desktop)\n\n## 🛠️ Установка и запуск\n\n```bash\n# Клонирование репозитория\ncd mcp-rag-service\n\n# Установка в режиме разработки\npip install -e .\n\n# Или с dev зависимостями\npip install -e \".[dev]\"\n```\n\n### Запуск через Docker (Рекомендуется)\n1. Сборка Docker образа:\n```bash\ndocker build -t mcp-rag-service:latest .\n```\n\n2. Запуск контейнера:\n```bash\ndocker run --rm -it \\\n  --network=\"host\" \\\n  -v \"/path/to/your/rag-server/data:/data\" \\\n  mcp-rag-service:latest\n```\n\nКонтейнеру нужен доступ к RAG серверу (по умолчанию http://localhost:8000) и к файлу базы данных rag.duckdb.\n\n- `--network=\"host\"`: Позволяет контейнеру обращаться к localhost хост-машины.\n- `-v \"/path/to/your/rag-server/data:/data\"`: Монтирует папку с rag.duckdb внутрь контейнера.\n\n### Настройка MCP клиента (например, Cursor или Claude Desktop)\n\nДобавьте в конфигурационный файл вашего клиента:\n\n``…","publisher":null,"homepage":"https://github.com/example/mcp-rag-service","repository":"https://github.com/example/mcp-rag-service","version":"1.0.0","license":"MIT","protocols":["mcp"],"tags":["duckdb","embeddings","mcp","rag","vector-search"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_niksh06-rag-duckdb-with-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"data.database","name":"Databases","confidence":0.733,"provenance":"derived"}],"categories":["data"],"language":"ru"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"iflow-mcp_niksh06-rag-duckdb-with-mcp","registry":"pypi","observedAt":"2026-11-09T10:23:11.864Z","publishedAt":"2026-02-26T15:46:49.992133Z","latestVersion":"1.0.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_niksh06-rag-duckdb-with-mcp","url":"https://pypi.org/project/iflow-mcp_niksh06-rag-duckdb-with-mcp/","firstSeenAt":"2026-09-09T20:24:34.131Z","fetchedAt":"2026-11-09T10:21:15.398Z","normalizedAt":"2026-11-09T10:21:15.398Z"}]},"firstSeenAt":"2026-09-09T20:24:34.131Z","updatedAt":"2026-11-09T10:23:11.864Z"}