AgentRender MCP Server
Screenshot, PDF, and structured extract for any public URL
AgentRender is a Web & Search MCP (Model Context Protocol) server: Screenshot, PDF, and structured extract for any public URL. It is MIT-licensed and self-hosted from its source repository. Listed on MCP Collection since September 2026.
About AgentRender
MCP + REST for AI agents: render any public URL to screenshot, PDF, or structured extract with receipts. Remote MCP and free tier available.
How to connect AgentRender to Claude, Cursor or VS Code
AgentRender is self-hosted. Install it from the source repository, then register its start command in your MCP client's config (Claude Code, Cursor, Windsurf or VS Code).
{
"mcpServers": {
"agentrender": {
"command": "<start command from the README>",
"args": []
}
}
}The exact command (often npx, uvx or docker) is in the project README at github.com/corbinvachal48/agentrender-mcp.
AgentRender FAQ
What is AgentRender?
AgentRender is a Model Context Protocol (MCP) server in the Web & Search category. Screenshot, PDF, and structured extract for any public URL. MCP servers expose tools that AI assistants like Claude can call during a conversation.
How do I use AgentRender with Claude or Cursor?
AgentRender is self-hosted. Install it from the source repository, then register its start command in your MCP client's config (Claude Code, Cursor, Windsurf or VS Code).
Is AgentRender free to use?
AgentRender is published under the MIT license, so the software itself is free to run. Hosted or API-backed servers may have their own usage tiers; check the project homepage.
Where is the source code for AgentRender?
The source is at github.com/corbinvachal48/agentrender-mcp.