Skip to main content
Paste these into an agent’s system prompt to encode the platform’s object model, safety rules, and error handling. Pick the variant matching your agent’s surface.

Cross-surface platform prompt

Works for any agent operating Reply.io, regardless of access layer:

MCP variant

For agents connected to the Reply MCP server, use the canonical MCP prompt — it adds tool-annotation gating, response-envelope parsing, and the MCP-specific failure guidance:

MCP drop-in system prompt

The canonical prompt for MCP agents, maintained with the MCP docs.

CLI variant

For coding agents that shell out to the reply CLI:

When to hand the agent a Skill instead

If your agent platform supports skills (e.g. Claude Code), install the Reply Agent Skill rather than writing procedure into the prompt — it packages the workflows above with verification steps and confirmation gates, and stays updated with the CLI. Keep the CLI variant prompt as a fallback for platforms without skill support.