Add billing to keep writing trusted context after the trial.
Tell your agent this
Open Claude Code, Cursor, or Codex and paste this:
Agent setup prompt
Set up ChatData for this AI client. Use https://getchatdata.com/agents.md as the source of truth. Claude Code should install both ChatData MCP and the ChatData Claude plugin, then let ChatData own the Claude Code status line by default. Cursor and Codex should use ChatData MCP only. After setup, run chatdata_doctor and tell me the result.
Claude installs hosted ChatData MCP plus the ChatData Claude plugin. The plugin adds /chatdata: commands and Claude-only hooks; plugin startup plus /chatdata:status install the ChatData status line by default.
MCP only
Cursor
Cursor uses hosted ChatData MCP. Do not install the Claude plugin.
MCP only
Codex
Codex uses hosted ChatData MCP when remote HTTP MCP is available. Do not use /chatdata: slash commands.
API keys and MCP snippets
Create a named key here, then copy the snippet for Claude Code, Cursor, Codex, or another MCP client. ChatData shows the raw key once.
Create a new API key
Use a label you will recognize later, such as Cursor on work laptop. ChatData shows the key once and stores only a hash.
Create a key to fill the snippets below.
Loading existing API keys.
Claude Code MCP JSON
Loading Claude Code MCP snippet.
Add this under your Claude Code MCP config. Then install the ChatData plugin below, reload plugins, and run /chatdata:status.
Cursor MCP JSON
Loading Cursor MCP snippet.
Add this to Cursor MCP settings. Then ask Cursor to run the ChatData doctor and pull approved context.
Codex MCP JSON
Loading Codex MCP snippet.
Use this when your Codex build supports remote HTTP MCP servers. Codex stays MCP-only and does not run /chatdata: commands.