{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_wvrzxvr4hehq","handle":"ragify-docs-mcp","url":"https://wellknown.network/agents/ragify-docs-mcp","links":{"self":"https://wellknown.network/agents/ragify-docs-mcp/record.json","html":"https://wellknown.network/agents/ragify-docs-mcp","markdown":"https://wellknown.network/agents/ragify-docs-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ragify-docs-mcp","status":"https://wellknown.network/api/v1/agents/ragify-docs-mcp/status","claim":"https://wellknown.network/agents/ragify-docs-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ragify-docs-mcp/claim.json","badge":"https://wellknown.network/agents/ragify-docs-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:ragify-docs-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ragify-docs-mcp","summary":"Recursively scrapes websites and builds a localized memory context to return specific reference text chunks.","description":"# 🔌 RAGify Docs: Recursive Documentation Scraper MCP Server \n \nA production-ready Model Context Protocol (MCP) server that empowers AI agents to recursively scrape entire software documentation sites, compile them into an in-memory vector store, and provide accurate, context-grounded answers to developer questions. \n \nBuilt using the **FastMCP Framework**, **LangChain**, and **Ollama**, this server lets tools like Claude Desktop, Cursor, or Zed read documentation pages in real-time to resolve coding problems without leaving the chat interface. \n \n--- \n \n## 🔥 Key Features \n \n- **Recursive Deep Scraping:** Crawls documentation sites up to two levels deep out of the box using custom beautifulsoup extraction. \n- **Dynamic Context Assembly:** Automatically splits raw website texts into clean, code-aware semantic blocks. \n- **High-Diversity MMR Search:** Uses Maximal Marginal Relevance to fetch contrasting context points rather than duplicating search matches from single sections. \n- **Local-First Architecture:** Leverages a lightweight in-memory vector index alongside local `llama3.2` models for privacy and cost efficiency. \n- **Safe Data Pipeline:** Explicitly channels all background terminal metrics into `stderr` to avoid protocol communication corruption over standard I/O channels. \n \n--- \n \n## 🛠️ Prerequisites \n \nBefore installing the server, ensure your local environment contains the following applications: \n \n- **Python:** version 3.10 or higher. \n- **Ollama:** Installed and running locally with the target model pulled: \n  ```bash \n  ollama pull llama3.2 \n  ``` \n \n--- \n \n## 📦 Installation & Setup \n \nFollow these steps to download and configure the project directory on your local machine. \n \n### 1. Clone and Navigate to the Project \n \n```bash \ngit clone https://github.com \ncd ragify_docs_2.0 \n``` \n \n### 2. Set Up a Virtual Environment \n \nCreate and boot up an isolated Python runtime container to avoid package conflicts: \n \n```powershell \n# Windows PowerShell \np…","publisher":null,"homepage":null,"repository":null,"version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:ragify-docs-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.web-scraping","name":"Web Scraping","confidence":1,"provenance":"derived"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":1,"provenance":"derived"},{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.779,"provenance":"derived"},{"slug":"communication.chat","name":"Team Chat","confidence":0.768,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.756,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["communication","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":"ragify-docs-mcp","registry":"pypi","observedAt":"2026-09-10T11:28:08.329Z","publishedAt":"2026-07-30T10:48:19.781544Z","latestVersion":"0.2.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ragify-docs-mcp","url":"https://pypi.org/project/ragify-docs-mcp/","firstSeenAt":"2026-09-10T11:25:56.104Z","fetchedAt":"2026-09-10T11:25:56.104Z","normalizedAt":"2026-09-10T11:25:56.104Z"}]},"firstSeenAt":"2026-09-10T11:25:56.104Z","updatedAt":"2026-09-10T11:28:08.329Z"}