{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_ruptq3frwgw6","handle":"iflow-mcp-digital-duck-st-rag-mcp","url":"https://wellknown.network/agents/iflow-mcp-digital-duck-st-rag-mcp","links":{"self":"https://wellknown.network/agents/iflow-mcp-digital-duck-st-rag-mcp/record.json","html":"https://wellknown.network/agents/iflow-mcp-digital-duck-st-rag-mcp","markdown":"https://wellknown.network/agents/iflow-mcp-digital-duck-st-rag-mcp/record.md","api":"https://wellknown.network/api/v1/agents/iflow-mcp-digital-duck-st-rag-mcp","status":"https://wellknown.network/api/v1/agents/iflow-mcp-digital-duck-st-rag-mcp/status","claim":"https://wellknown.network/agents/iflow-mcp-digital-duck-st-rag-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/iflow-mcp-digital-duck-st-rag-mcp/claim.json","badge":"https://wellknown.network/agents/iflow-mcp-digital-duck-st-rag-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/iflow-mcp-digital-duck-st-rag-mcp/history","tools":"https://wellknown.network/api/v1/agents/iflow-mcp-digital-duck-st-rag-mcp/tools"},"ard":{"identifier":"urn:air::server:iflow-mcp-digital-duck-st-rag-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"iflow-mcp_digital-duck-st_rag_mcp","summary":"RAG MCP Server with calculator, trigonometric, and stock quote tools","description":"# RAG MCP\n\nThe RAG system is particularly well-designed, using sentence transformers to build rich contextual embeddings and performing semantic search to find the most relevant tools for each query. This makes the system much more robust than traditional keyword-based approaches.\n\n## What is [MCP](https://modelcontextprotocol.io/introduction)\n\nMCP stands for Model Context protocol, it helps provide contexts to LLM model for tool-use.\n\n![MCP Arch](./docs/mcp-arch.png)\n\n## Architecture Diagram \n\nMCP with RAG\n\n![RAG MCP Arch](./docs/st_rag_mcp-arch.png)\n\nThe Mermaid diagram illustrates:\n\n- **7 Distinct Layers** with color coding for easy understanding\n- **Complete Data Flow** from user input through RAG processing to tool execution\n- **Decision Tree Logic** showing how queries are routed through different parsing modes\n- **RAG Integration** highlighting how semantic search enhances tool selection\n- **Multi-LLM Support** showing integration with Google, OpenAI, and Anthropic\n- **MCP Server Integration** with tool discovery and execution\n- **Data Persistence** including SQLite storage and caching mechanisms\n\n## Key Features\n\n![RAG MCP UI](./docs/st_rag_mcp_ui.png)\n\n1. **Intelligent Tool Selection** using RAG to find relevant tools dynamically\n2. **Flexible Parsing Strategy** with fallback mechanisms (RAG → LLM → Rule-based)\n3. **Comprehensive Logging** for debugging and performance analysis\n4. **Caching Strategy** for efficient server discovery\n5. **Multi-Provider LLM Support** for flexibility and redundancy\n\n## Setup\n```bash\n# create a virtual environment\nconda create -n mcp\nconda activate mcp\n\n# obtain source code\ngit clone https://github.com/digital-duck/st_rag_mcp.git\ncd st_rag_mcp\npip install -r requirements.txt\n\n# open 1st terminal\ncd src\npython mcp_server.py\n\n# in 2nd terminal\nconda activate mcp\ncd src\nstreamlit run mcp_client.py\n```\n\n## Demo Video\n- [MCP + RAG](https://youtu.be/K2jgrMsgZxA)\n\n## References\n\n- https://www.anthropic.com/news/integrations\n- [RAG-MC…","publisher":null,"homepage":null,"repository":null,"version":"0.1.1","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:iflow-mcp_digital-duck-st_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"}},"derived":{"capabilities":[{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"derived"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":0.791,"provenance":"derived"},{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.779,"provenance":"derived"},{"slug":"data.database","name":"Databases","confidence":0.768,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"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_digital-duck-st_rag_mcp","registry":"pypi","observedAt":"2026-11-09T08:24:33.970Z","publishedAt":"2026-02-11T15:35:58.881810Z","latestVersion":"0.1.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"iflow-mcp_digital-duck-st_rag_mcp","url":"https://pypi.org/project/iflow-mcp_digital-duck-st_rag_mcp/","firstSeenAt":"2026-09-09T18:21:55.797Z","fetchedAt":"2026-11-09T08:22:53.172Z","normalizedAt":"2026-11-09T08:22:53.172Z"}]},"firstSeenAt":"2026-09-09T18:21:55.797Z","updatedAt":"2026-11-09T08:24:33.970Z"}