{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_6czuz4mp2fbc","handle":"singlefile-mcp","url":"https://wellknown.network/agents/singlefile-mcp","links":{"self":"https://wellknown.network/agents/singlefile-mcp/record.json","html":"https://wellknown.network/agents/singlefile-mcp","markdown":"https://wellknown.network/agents/singlefile-mcp/record.md","api":"https://wellknown.network/api/v1/agents/singlefile-mcp","status":"https://wellknown.network/api/v1/agents/singlefile-mcp/status","claim":"https://wellknown.network/agents/singlefile-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/singlefile-mcp/claim.json","badge":"https://wellknown.network/agents/singlefile-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:singlefile-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"singlefile-mcp","summary":"MCP server for intelligent web content extraction using single-file and trafilatura","description":"# Single-File MCP Server\n\nA powerful Model Context Protocol (MCP) server that provides intelligent web content extraction using [single-file](https://github.com/gildas-lormeau/SingleFile) and [trafilatura](https://github.com/adbar/trafilatura). Perfect for AI agents that need to access and analyze web content from JavaScript-heavy sites.\n\n**GitHub Repository**: [https://github.com/kwinsch/singlefile-mcp](https://github.com/kwinsch/singlefile-mcp)\n\n## Features\n\n### 🌐 Universal Web Content Access\n- **JavaScript Support**: Handles modern SPA/React/Vue apps that require browser rendering\n- **Clean Content Extraction**: Uses Mozilla's Readability algorithm via trafilatura\n- **Rich Metadata**: Extracts title, author, date, description, and more\n- **Multiple Output Formats**: Raw HTML or clean markdown-like content\n\n### 📄 Smart Pagination & Token Management\n- **Flexible Pagination**: Offset/limit system like file reading tools\n- **Token Limits**: Configurable max tokens (up to 25,000)\n- **Smart Truncation**: Summary mode shows beginning + end, truncate mode cuts cleanly\n- **Navigation Hints**: Clear guidance on how to continue reading large documents\n\n### ⚡ Performance & Control\n- **Selective Loading**: Block images/scripts for faster processing\n- **Content Compression**: Optional HTML compression\n- **Timeout Protection**: Configurable timeouts prevent hanging\n- **Error Handling**: Graceful degradation when extraction fails\n\n## Installation\n\n### Prerequisites\n- Python 3.8+\n- [single-file CLI](https://github.com/gildas-lormeau/SingleFile) - Web page capture tool\n- Node.js 16+ (for single-file)\n- A supported browser (Chromium, Chrome, Edge, Firefox, etc.)\n\n### Install single-file CLI\n\nThe [single-file CLI](https://github.com/gildas-lormeau/SingleFile/tree/master/cli) is essential for this MCP server to work. It uses a real browser engine to accurately capture JavaScript-rendered content.\n\n```bash\nnpm install -g single-file-cli\n```\n\n## Usage with Claude Code\n\n### Quick Ins…","publisher":null,"homepage":"https://github.com/kwinsch/singlefile-mcp","repository":"https://github.com/kwinsch/singlefile-mcp","version":"0.1.1","license":null,"protocols":["mcp"],"tags":["mcp","model-context-protocol","web-scraping","content-extraction","single-file","trafilatura","ai","llm"],"pricing":null,"endpoints":[{"url":"pypi:singlefile-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"documents.extraction","name":"Data Extraction","confidence":1,"provenance":"derived"},{"slug":"data.web-scraping","name":"Web Scraping","confidence":1,"provenance":"declared"},{"slug":"dev.version-control","name":"Version Control","confidence":0.825,"provenance":"derived"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":0.791,"provenance":"derived"}],"categories":["data","dev","documents","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":"singlefile-mcp","registry":"pypi","observedAt":"2026-09-10T12:23:31.004Z","publishedAt":"2025-06-06T06:28:00.012079Z","latestVersion":"0.1.1"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"singlefile-mcp","url":"https://pypi.org/project/singlefile-mcp/","firstSeenAt":"2026-09-10T12:22:16.821Z","fetchedAt":"2026-09-10T12:22:16.821Z","normalizedAt":"2026-09-10T12:22:16.821Z"}]},"firstSeenAt":"2026-09-10T12:22:16.821Z","updatedAt":"2026-09-10T12:23:31.004Z"}