{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_v6347h8nx7gx","handle":"agent-rag-mcp","url":"https://wellknown.network/agents/agent-rag-mcp","links":{"self":"https://wellknown.network/agents/agent-rag-mcp/record.json","html":"https://wellknown.network/agents/agent-rag-mcp","markdown":"https://wellknown.network/agents/agent-rag-mcp/record.md","api":"https://wellknown.network/api/v1/agents/agent-rag-mcp","status":"https://wellknown.network/api/v1/agents/agent-rag-mcp/status","claim":"https://wellknown.network/agents/agent-rag-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/agent-rag-mcp/claim.json","badge":"https://wellknown.network/agents/agent-rag-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/agent-rag-mcp/history","tools":"https://wellknown.network/api/v1/agents/agent-rag-mcp/tools"},"ard":{"identifier":"urn:air::server:agent-rag-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"agent-rag-mcp","summary":"RAG MCP server: ChromaDB + sentence-transformers, exposes ingest/search/list/delete tools.","description":"# Agent_rag\n\nAgent_rag is a RAG (Retrieval-Augmented Generation) MCP (Model Context Protocol) Server. It uses ChromaDB for vector storage and provides flexible embedding options—from lightweight Ollama integration to local ONNX models—with zero external dependencies.\n\n## Available Tools\n\nThis server exposes several MCP tools for the orchestrator (`Agent_head`) or any other MCP client:\n\n- **`rag_ingest`** — Ingest documents, directories, or raw text into a collection\n- **`rag_search`** — Perform semantic search against your knowledge base\n- **`rag_list_collections`** — List all active collections\n- **`rag_delete_collection`** — Delete a specific collection\n\n## Features\n\n- **Flexible Embedding Providers** — Choose your embedding backend:\n  - **Ollama** (~50 MB): Lightweight, runs with Ollama service—94% smaller than torch-based setup\n  - **Local ONNX** (~300 MB): Fully offline with CPU/GPU support—no external services needed\n  - **GPU-Accelerated** (~1.2 GB): PyTorch + sentence-transformers for maximum performance\n- **ChromaDB Integration**: Persistent vector database for efficient semantic search\n- **FastMCP Built-in**: Asynchronous, thread-safe tool execution\n- **Easy Configuration**: Flexible `config.yaml` for chunk size, collections, embedding models, and provider selection\n- **Zero External Dependencies**: No API keys required—everything runs locally\n\n## Quick Start\n\nFor a complete installation guide with size comparisons, troubleshooting, and provider-specific setup:\n\n👉 **See [INSTALLATION.md](INSTALLATION.md)**\n\n## Installation & Usage\n\n### Interactive Setup (Recommended)\n\n```bash\ncd Agent_rag\npython setup_agent_rag.py\n```\n\nThis interactive script guides you through provider selection and runs the appropriate installation command.\n\n### Direct Installation\n\n**For Ollama** (lightweight, ~50 MB):\n\n```bash\nuv install .[ollama]\npython server.py\n```\n\n**For Local Offline** (ONNX, ~300 MB):\n\n```bash\nuv install .[local]\npython server.py\n```\n\n**For GPU** (PyTorch accel…","publisher":{"name":"Tharindumendis","url":null},"homepage":null,"repository":null,"version":"1.1.9","license":null,"protocols":["mcp"],"tags":["agent","chromadb","fastmcp","llm","mcp","rag"],"pricing":null,"endpoints":[{"url":"pypi:agent-rag-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"}],"categories":["data"],"language":"en"},"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":"agent-rag-mcp","registry":"pypi","observedAt":"2026-11-08T22:24:58.223Z","publishedAt":"2026-07-12T17:34:48.222950Z","latestVersion":"1.1.9"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"agent-rag-mcp","url":"https://pypi.org/project/agent-rag-mcp/","firstSeenAt":"2026-09-09T08:21:14.710Z","fetchedAt":"2026-11-08T22:23:54.080Z","normalizedAt":"2026-11-08T22:23:54.080Z"}]},"firstSeenAt":"2026-09-09T08:21:14.710Z","updatedAt":"2026-11-08T22:24:58.223Z"}