{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_vy4xdj9s5yy8","handle":"hound-mcp-2","url":"https://wellknown.network/agents/hound-mcp-2","links":{"self":"https://wellknown.network/agents/hound-mcp-2/record.json","html":"https://wellknown.network/agents/hound-mcp-2","markdown":"https://wellknown.network/agents/hound-mcp-2/record.md","api":"https://wellknown.network/api/v1/agents/hound-mcp-2","status":"https://wellknown.network/api/v1/agents/hound-mcp-2/status","claim":"https://wellknown.network/agents/hound-mcp-2/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/hound-mcp-2/claim.json","badge":"https://wellknown.network/agents/hound-mcp-2/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/hound-mcp-2/history","tools":"https://wellknown.network/api/v1/agents/hound-mcp-2/tools"},"ard":{"identifier":"urn:air::server:hound-mcp-2","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"hound-mcp","summary":"Web research for AI agents. Fetch any page with anti-bot bypass plus web search. $0 forever. No scrapling dependency: hound uses primp + patchright directly. Graceful degradation when browser deps are unavailable (HTTP-only mode on Termux/Android). Token-optimized tool definitions, polished cross-p…","description":"<div align=\"center\">\n\n<img src=\"https://raw.githubusercontent.com/dondai44423/master-fetch/master/docs/hound-logo.png\" alt=\"Hound logo\" width=\"128\">\n\n# 🐕 Hound\n\n**Give your AI agent the web. $0. Two commands. No keys.**\n\nFetch · crawl · bypass bot walls · read PDFs (even scanned) · search the web\nOne MCP server · one warm browser · zero accounts · runs on your machine\n\n[![PyPI](https://img.shields.io/pypi/v/hound-mcp.svg?label=pypi)](https://pypi.org/project/hound-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/hound-mcp.svg)](https://pypi.org/project/hound-mcp/)\n[![License: MIT](https://img.shields.io/pypi/l/hound-mcp.svg)](LICENSE)\n[![CI](https://img.shields.io/github/actions/workflow/status/dondai44423/master-fetch/ci.yml?label=CI)](https://github.com/dondai44423/master-fetch/actions/workflows/ci.yml)\n[![Downloads](https://static.pepy.tech/badge/hound-mcp)](https://pepy.tech/project/hound-mcp)\n[![GitHub stars](https://img.shields.io/github/stars/dondai44423/master-fetch?style=social)](https://github.com/dondai44423/master-fetch/stargazers)\n\n[![ko-fi](https://ko-fi.com/img/githubbutton_sm.svg)](https://ko-fi.com/G5Y624N5RE)\n\n```bash\npip install hound-mcp[all] && playwright install chromium\n```\n\n[Install](#-install) · [The 6 tools](#-the-6-tools) · [Search](#-local-keyless-search) · [Comparison](#-comparison-free-tools) · [Gotchas](#-known-gotchas) · [Honest limits](#-honest-limits)\n\n</div>\n\n<br>\n\n<div align=\"center\">\n<img src=\"https://raw.githubusercontent.com/dondai44423/master-fetch/master/docs/hound-hero.png\" alt=\"Hound gives your AI agent the web\" width=\"860\">\n</div>\n\n---\n\n## 🎬 Demo\n\nSame prompt, three tools. Hound does the whole thing on its own, search + fetch + crawl, locally. The others get stuck on the parts they don't do.\n\n<div align=\"center\"><b>OpenCode + Hound</b></div>\n\n<video src=\"https://github.com/user-attachments/assets/4e69e476-9c46-40cd-9bdf-f1b45882ac3e\" controls muted width=\"860\"></video>\n\n<div align=\"center\"><b>Pi + Hound</b></div>…","publisher":null,"homepage":null,"repository":"https://github.com/dondai44423/master-fetch/blob/master/CHANGELOG.md","version":"13.2.0","license":null,"protocols":["mcp"],"tags":["ai-agent","anti-bot","cloudflare-bypass","content-extraction","mcp","mcp-server","web-scraping"],"pricing":null,"endpoints":[{"url":"pypi:hound-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"}},"derived":{"capabilities":[{"slug":"data.web-scraping","name":"Web Scraping","confidence":1,"provenance":"declared"},{"slug":"data.web-search","name":"Web Search","confidence":0.894,"provenance":"derived"},{"slug":"infra.browser-automation","name":"Browser Automation","confidence":0.836,"provenance":"derived"},{"slug":"documents.extraction","name":"Data Extraction","confidence":0.713,"provenance":"derived"},{"slug":"infra.cloud","name":"Cloud Platforms","confidence":0.713,"provenance":"derived"}],"categories":["data","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":"hound-mcp","registry":"pypi","observedAt":"2026-10-28T02:26:59.663Z","publishedAt":"2026-08-26T10:42:52.181551Z","latestVersion":"13.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"hound-mcp","url":"https://pypi.org/project/hound-mcp/","firstSeenAt":"2026-09-09T17:21:24.640Z","fetchedAt":"2026-10-28T02:26:30.315Z","normalizedAt":"2026-10-28T02:26:30.315Z"}]},"firstSeenAt":"2026-09-09T17:21:24.640Z","updatedAt":"2026-10-28T02:26:59.663Z"}