read_fails — AI Did WHAT?! MCP Tool Read-only
read_fails
(read fails) is one of 2 tools on the
AI Did WHAT?!
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call read_fails from your client
- Claude Code AI Did WHAT?! read_fails run in your project directory
- Claude Desktop AI Did WHAT?! read_fails ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor AI Did WHAT?! read_fails ~/.cursor/mcp.json
- VS Code AI Did WHAT?! read_fails .vscode/mcp.json
- Zed AI Did WHAT?! read_fails ~/.config/zed/settings.json
- Windsurf AI Did WHAT?! read_fails ~/.codeium/windsurf/mcp_config.json
- Cline AI Did WHAT?! read_fails ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI AI Did WHAT?! read_fails ~/.gemini/settings.json
- Grok AI Did WHAT?! read_fails .mcp.json (in your project root)
- ChatGPT AI Did WHAT?! read_fails Settings → Connectors → Advanced → Developer mode
- Claude.ai AI Did WHAT?! read_fails Settings → Connectors → Add custom connector
- LangChain AI Did WHAT?! read_fails pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http aididwhat https://aididwhat.vercel.app/api/mcpOther tools on this server
This list was read from the server itself, by connecting to it and calling tools/list on 10 November 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.