{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_5hnx52mp79nd","handle":"mcp-docs-contributors-mcp-docs","url":"https://wellknown.network/agents/mcp-docs-contributors-mcp-docs","links":{"self":"https://wellknown.network/agents/mcp-docs-contributors-mcp-docs/record.json","html":"https://wellknown.network/agents/mcp-docs-contributors-mcp-docs","markdown":"https://wellknown.network/agents/mcp-docs-contributors-mcp-docs/record.md","api":"https://wellknown.network/api/v1/agents/mcp-docs-contributors-mcp-docs","status":"https://wellknown.network/api/v1/agents/mcp-docs-contributors-mcp-docs/status","claim":"https://wellknown.network/agents/mcp-docs-contributors-mcp-docs/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/mcp-docs-contributors-mcp-docs/claim.json","badge":"https://wellknown.network/agents/mcp-docs-contributors-mcp-docs/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/mcp-docs-contributors-mcp-docs/history","tools":"https://wellknown.network/api/v1/agents/mcp-docs-contributors-mcp-docs/tools"},"ard":{"identifier":"urn:air::server:mcp-docs-contributors-mcp-docs","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"mcp-docs","summary":"Turn any documentation site into an MCP server","description":"# MCP-Docs — Turn any docs site into an MCP server \n \nA Python package that scrapes documentation sites, indexes them with embeddings, and exposes them as MCP (Model Context Protocol) servers for LLM integration. \n \n## Features \n \n- **Web Scraping**: Uses Playwright to scrape JavaScript-rendered documentation sites \n- **Semantic Search**: Indexes documentation with embeddings for semantic search \n- **Multiple Embedding Providers**: Supports OpenAI and Azure OpenAI embeddings \n- **Vector Storage**: Uses ChromaDB for persistent vector storage \n- **MCP Server**: Automatically generates and runs MCP servers for each documentation project \n- **Project-Based**: Organizes documentation sites as separate projects \n- **CLI Tool**: Simple command-line interface for managing projects \n \n## Installation \n \n### From Source \n \n```bash \n# Clone the repository \ngit clone https://github.com/yourorg/mcp-docs.git \ncd mcp-docs \n \n# Create virtual environment \npython -m venv .venv \n \n# Activate virtual environment \n# On Windows (PowerShell): \n.\\.venv\\Scripts\\Activate.ps1 \n# On macOS/Linux: \nsource .venv/bin/activate \n \n# Install in editable mode \npip install -e \".[dev]\" \n \n# Install Playwright browsers \nplaywright install chromium \n``` \n \n### Dependencies \n \nThe project requires: \n- Python 3.8+ \n- Embedding provider credentials: \n  - OpenAI API key, OR \n  - Azure OpenAI (API key, endpoint, and deployment ID) \n- Playwright (for web scraping) \n- ChromaDB (for vector storage) \n \n## Quick Start \n \n### 1. Configure Embedding Provider \n \nSet up your embedding provider (OpenAI or Azure OpenAI): \n \n```bash \n# Interactive configuration (will prompt for provider selection) \nmcp-docs configure \n``` \n \nOr configure via command line: \n \n```bash \n# Configure OpenAI \nmcp-docs configure --provider openai --api-key sk-your-key-here \n \n# Configure Azure OpenAI \nmcp-docs configure --provider azure-openai --api-key your-key --endpoint https://your-resource.openai.azure.com --deployment-id text-embedding-a…","publisher":{"name":"mcp-docs contributors","url":null},"homepage":null,"repository":null,"version":"0.0.1","license":"MIT","protocols":["mcp"],"tags":["mcp","documentation","indexing","vector-search","embeddings","chromadb"],"pricing":null,"endpoints":[{"url":"pypi:mcp-docs","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","summary":"pypi","version":"pypi","description":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"code.documentation","name":"Code Documentation","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":1,"provenance":"derived"},{"slug":"dev.docs-lookup","name":"Documentation Lookup","confidence":1,"provenance":"derived"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.859,"provenance":"derived"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":0.836,"provenance":"derived"},{"slug":"dev.terminal","name":"Terminal & Shell","confidence":0.825,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.779,"provenance":"derived"}],"categories":["code","data","dev","infra"],"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":"mcp-docs","registry":"pypi","observedAt":"2026-10-28T11:27:05.892Z","publishedAt":"2025-11-16T12:27:40.837457Z","latestVersion":"0.0.1"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"mcp-docs","url":"https://pypi.org/project/mcp-docs/","firstSeenAt":"2026-09-10T01:20:09.500Z","fetchedAt":"2026-10-28T11:24:58.263Z","normalizedAt":"2026-10-28T11:24:58.263Z"}]},"firstSeenAt":"2026-09-10T01:20:09.500Z","updatedAt":"2026-10-28T11:27:05.892Z"}