{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_5etvfc3fnfcq","handle":"ragnet-mcp","url":"https://wellknown.network/agents/ragnet-mcp","links":{"self":"https://wellknown.network/agents/ragnet-mcp/record.json","html":"https://wellknown.network/agents/ragnet-mcp","markdown":"https://wellknown.network/agents/ragnet-mcp/record.md","api":"https://wellknown.network/api/v1/agents/ragnet-mcp","status":"https://wellknown.network/api/v1/agents/ragnet-mcp/status","claim":"https://wellknown.network/agents/ragnet-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/ragnet-mcp/claim.json","badge":"https://wellknown.network/agents/ragnet-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:ragnet-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"ragnet-mcp","summary":"Documentation RAG pipeline with a Textual dashboard and MCP server","description":"# RAGNet MCP\n\n**Give Claude access to any documentation you want.**\n\nRAGNet crawls documentation websites, stores them in a searchable database, and lets Claude search through them when you're coding. Instead of copy-pasting docs into your prompts, Claude can look things up itself.\n\n---\n\n## How It Works (Plain English)\n\n```\n┌─────────────────┐      stdio      ┌─────────────────┐\n│   Claude Code   │ ◄─────────────► │   RAGNet MCP    │\n│   (or Desktop)  │   (messages)    │   (this tool)   │\n└─────────────────┘                 └────────┬────────┘\n                                             │\n                                    HTTP     │\n                                             ▼\n                                    ┌─────────────────┐\n                                    │     Qdrant      │\n                                    │ (vector database)│\n                                    └─────────────────┘\n```\n\n**Three pieces:**\n\n1. **Claude** (the AI) - asks questions like \"how do I use AsyncWebCrawler?\"\n2. **RAGNet MCP** (this project) - receives the question, searches the database, returns relevant docs\n3. **Qdrant** (vector database) - stores all the documentation chunks and finds similar content\n\n**Important:** RAGNet is NOT a web server. It's a subprocess that Claude spawns and talks to via stdin/stdout (like two programs chatting through a pipe). Qdrant is the only actual server running on a port.\n\n---\n\n## Quick Start\n\n### What You'll Need\n\n- **Python 3.10 or newer** - [Download here](https://www.python.org/downloads/)\n- **Docker Desktop** - [Download here](https://www.docker.com/products/docker-desktop/) (for running Qdrant)\n- **OpenAI API key** - [Get one here](https://platform.openai.com/api-keys) (for generating embeddings)\n\n### Install from PyPI (Recommended)\n\n```bash\npip install ragnet-mcp\nragnet init\n```\n\n### Install from Source\n\n```bash\ngit clone https://github.com/orro3790/ragnet.git\ncd ragnet\npip install -e .\nragnet init\n```\n\nThe `ragnet init` command …","publisher":null,"homepage":null,"repository":null,"version":"0.2.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:ragnet-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":"commerce.ecommerce","name":"E-commerce Operations","confidence":0.791,"provenance":"derived"},{"slug":"ai.prompting","name":"Prompt Management","confidence":0.791,"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":["ai","commerce","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":"ragnet-mcp","registry":"pypi","observedAt":"2026-09-10T11:28:08.825Z","publishedAt":"2026-01-27T01:08:39.736478Z","latestVersion":"0.2.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"ragnet-mcp","url":"https://pypi.org/project/ragnet-mcp/","firstSeenAt":"2026-09-10T11:25:58.117Z","fetchedAt":"2026-09-10T11:25:58.117Z","normalizedAt":"2026-09-10T11:25:58.117Z"}]},"firstSeenAt":"2026-09-10T11:25:58.117Z","updatedAt":"2026-09-10T11:28:08.825Z"}