extract_html — AgentRead — bounded web context MCP Tool
extract_html
(extract html) is one of 3 tools on the
AgentRead — bounded web context
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call extract_html from your client
- Claude Code AgentRead — bounded web context extract_html run in your project directory
- Claude Desktop AgentRead — bounded web context extract_html ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AgentRead — bounded web context extract_html ~/.cursor/mcp.json
- VS Code AgentRead — bounded web context extract_html .vscode/mcp.json
- Zed AgentRead — bounded web context extract_html ~/.config/zed/settings.json
- Windsurf AgentRead — bounded web context extract_html ~/.codeium/windsurf/mcp_config.json
- Cline AgentRead — bounded web context extract_html ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AgentRead — bounded web context extract_html ~/.gemini/settings.json
- Grok AgentRead — bounded web context extract_html .mcp.json (in your project root)
- ChatGPT AgentRead — bounded web context extract_html Settings → Connectors → Advanced → Developer mode
- Claude.ai AgentRead — bounded web context extract_html Settings → Connectors → Add custom connector
- LangChain AgentRead — bounded web context extract_html pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http agentread https://agentread-json-api.army20160422.chatgpt.site/agent/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 26 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.