{
  "markdown": "# DMCA Takedown MCP Server\n\n> **The first DMCA takedown & host-reveal [MCP](https://modelcontextprotocol.io) server.**\n> Connect it to Claude (or any MCP client) and your AI agent can answer:\n> *“who really hosts this infringing site — even behind Cloudflare — where does\n> the DMCA/abuse notice go, and how do I actually get it taken down?”*\n\nHosted and operated by [Lawyerd](https://lawyerd.net), a counsel-led content-removal\npractice. This repository is the public home and documentation for the server;\nit is a **remote, hosted MCP server** — there is nothing to install or run\nyourself. Just point your agent at the endpoint.\n\n- **Endpoint:** `https://mcp.lawyerd.net/takedown` (Streamable HTTP)\n- **Alias:** `https://mcp.lawyerd.net/mcp`\n- **Registry:** [`net.lawyerd/takedown`](https://registry.modelcontextprotocol.io/v0/servers?search=lawyerd) in the official MCP Registry\n- **Cost:** free, no account, rate-limited\n- **Discovery:** [`/.well-known/mcp.json`](https://mcp.lawyerd.net/.well-known/mcp.json)\n\n---\n\n## Quick start\n\nAdd the server to Claude Code / Claude Desktop:\n\n```bash\nclaude mcp add --transport http lawyerd https://mcp.lawyerd.net/takedown\n```\n\nOr add it to any MCP client config (`mcpServers`):\n\n```json\n{\n  \"mcpServers\": {\n    \"lawyerd\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.lawyerd.net/takedown\"\n    }\n  }\n}\n```\n\nThen just ask your assistant, in your own words:\n\n> *“Someone reposted my photo set and is selling prints at `https://example-infringer.com`.\n> Who hosts it and how do I take it down?”*\n\nThe agent chains the three tools below and hands you a plain-language answer.\n\n---\n\n## Tools\n\n### `resolve_host`\nLook up who hosts a URL and where a DMCA/abuse notice would go. Identifies the\nplatform, the CDN/proxy in front (e.g. **Cloudflare**, DDoS-Guard), or the\ndirect hosting provider and its abuse contact. For domains whose real host has\nalready been revealed from behind a proxy, it returns that host immediately;\nfor a domain still hidden behind a proxy it says so honestly — revealing the\ntrue host means initiating an abuse report. **Read-only; files nothing.**\n\n### `assess_takedown`\nThe plan for a takedown of a specific URL: the route it would follow (host\nabuse, platform form, or reveal-first), what the rights holder must supply\n(proof of ownership and a one-time signed attestation), the step-by-step\nprocess, and the legal caveats — including **17 U.S.C. §512(f)** and scope\nlimits. Read-only; it does not judge the merits of the claim.\n\n### `start_takedown`\nReturns a secure onboarding link to actually begin a takedown. A human opens\nit once in a browser to identify themselves, sign the authorization (the one\nstep that legally requires a human), and provide proof of ownership. **Nothing\nis filed by the agent.**\n\n---\n\n## Example\n\n```jsonc\n// tools/call → resolve_host  { \"url\": \"https://example-infringer.com\" }\n{\n  \"domain\": \"example-infringer.com\",\n  \"frontedBy\": \"cdn_proxy\",\n  \"proxy\": { \"name\": \"Cloudflare\" },\n  \"realHostHidden\": true,\n  \"takedownRoute\": \"needs_reveal\",\n  \"nextStep\": \"The site is behind Cloudflare — the real host is hidden. Revealing it requires initiating an abuse report; start a takedown to do that.\"\n}\n```\n\nFor a domain already revealed, `resolve_host` returns the real host and its\nabuse email directly, with `revealSource: \"cached_reveal\"`.\n\n---\n\n## What this is — and is not\n\n- ✅ A **lookup and planning** layer for DMCA / abuse takedowns, callable by AI agents.\n- ✅ Honest about what it knows: it never invents an abuse contact, and it does\n  not claim a synchronous “reveal behind Cloudflare” it cannot actually perform\n  without filing.\n- ❌ **Not** an auto-filing bot. A DMCA notice is signed by the rights holder\n  under penalty of perjury; that signature is always made by a human.\n- ❌ **Not** legal advice, and it does not guarantee removal.\n- ❌ **Not** a tool for suppressing lawful content. Copyright, trademark and\n  brand-impersonation matters only — lawful criticism, reviews and journalism\n  are declined at intake.\n\nThe actual enforcement — revealing the real host, filing the notice, following\nup, and confirming the content is genuinely gone — is done by Lawyerd under\nqualified counsel. The MCP server is the front door; [lawyerd.net](https://lawyerd.net)\nis the practice behind it.\n\n---\n\n## Keywords\n\nDMCA takedown · MCP server · Model Context Protocol · AI agent · host reveal ·\nfind the real host behind Cloudflare · abuse contact lookup · copyright\ntakedown · brand protection · content removal · Claude · takedown automation.\n\n## Links\n\n- Website: <https://lawyerd.net>\n- MCP endpoint: <https://mcp.lawyerd.net/takedown>\n- Official MCP Registry entry: <https://registry.modelcontextprotocol.io/v0/servers?search=lawyerd>\n- Model Context Protocol: <https://modelcontextprotocol.io>\n- Contact: dmca@lawyerd.net\n\n## License\n\nDocumentation in this repository is released under the [MIT License](LICENSE).\nThe hosted service, its tool implementations and the underlying host-resolution\ndata are proprietary to Lawyerd and are **not** included here.\n",
  "bytes": 5065,
  "sha": "a67878c44ffc23d08c6704912adf3801c91549760ecec8490a4f67575861a67b",
  "repo_slug": "lawyerd999/dmca-takedown-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_net_lawyerd_takedown_9eed0622/readme"
}