{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_xzea7um6gdhn","handle":"iflow-mcp-mcp-rag","url":"https://wellknown.network/agents/iflow-mcp-mcp-rag","links":{"self":"https://wellknown.network/agents/iflow-mcp-mcp-rag/record.json","html":"https://wellknown.network/agents/iflow-mcp-mcp-rag","markdown":"https://wellknown.network/agents/iflow-mcp-mcp-rag/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-mcp-rag","status":"https://wellknown.network/api/v1/agents/iflow-mcp-mcp-rag/status","claim":"https://wellknown.network/agents/iflow-mcp-mcp-rag/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-mcp-rag/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-mcp-rag/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-mcp-rag/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-mcp-rag/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-mcp-rag","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_mcp-rag","summary":"A Simple MCP RAG with GroundX","description":"# MCP-RAG: Model Context Protocol with RAG 🚀\n\nA powerful and efficient RAG (Retrieval-Augmented Generation) implementation using GroundX and OpenAI, built with Modern Context Processing (MCP).\n\n## 🌟 Features\n\n- **Advanced RAG Implementation**: Utilizes GroundX for high-accuracy document retrieval\n- **Model Context Protocol**: Seamless integration with MCP for enhanced context handling\n- **Type-Safe**: Built with Pydantic for robust type checking and validation\n- **Flexible Configuration**: Easy-to-customize settings through environment variables\n- **Document Ingestion**: Support for PDF document ingestion and processing\n- **Intelligent Search**: Semantic search capabilities with scoring\n\n## 🛠️ Prerequisites\n\n- Python 3.12 or higher\n- OpenAI API key\n- GroundX API key\n- MCP CLI tools\n\n## 📦 Installation\n\n1. Clone the repository:\n```bash\ngit clone <repository-url>\ncd mcp-rag\n```\n\n2. Create and activate a virtual environment:\n```bash\nuv sync\nsource .venv/bin/activate  # On Windows, use `.venv\\Scripts\\activate`\n```\n\n## ⚙️ Configuration\n\n1. Copy the example environment file:\n```bash\ncp .env.example .env\n```\n\n2. Configure your environment variables in `.env`:\n```env\nGROUNDX_API_KEY=\"your-groundx-api-key\"\nOPENAI_API_KEY=\"your-openai-api-key\"\nBUCKET_ID=\"your-bucket-id\"\n```\n\n## 🚀 Usage\n\n### Starting the Server\n\nRun the inspect server using:\n```bash\nmcp dev server.py\n```\n\n### Document Ingestion\n\nTo ingest new documents:\n```python\nfrom server import ingest_documents\n\nresult = ingest_documents(\"path/to/your/document.pdf\")\nprint(result)\n```\n\n### Performing Searches\n\nBasic search query:\n```python\nfrom server import process_search_query\n\nresponse = process_search_query(\"your search query here\")\nprint(f\"Query: {response.query}\")\nprint(f\"Score: {response.score}\")\nprint(f\"Result: {response.result}\")\n```\n\nWith custom configuration:\n```python\nfrom server import process_search_query, SearchConfig\n\nconfig = SearchConfig(\n    completion_model=\"gpt-4\",\n    bucket_id=\"custom-bucket-id\"\n…","publisher":null,"homepage":null,"repository":null,"version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_mcp-rag","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.791,"provenance":"derived"}],"categories":["data","dev"],"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":"iflow-mcp_mcp-rag","registry":"pypi","observedAt":"2026-09-15T19:23:09.279Z","publishedAt":"2025-12-01T08:27:24.718911Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_mcp-rag","url":"https://pypi.org/project/iflow-mcp_mcp-rag/","firstSeenAt":"2026-09-09T20:23:36.901Z","fetchedAt":"2026-09-15T19:21:12.410Z","normalizedAt":"2026-09-15T19:21:12.410Z"}]},"firstSeenAt":"2026-09-09T20:23:36.901Z","updatedAt":"2026-09-15T19:23:09.279Z"}