REA's guided MCP prompts give an agent an investigation starting point, but a prompt is not a connection or a provider. Configure the local server in a compatible client, inspect the tools that register, and ask one bounded question about an authorized target. Preserve tool observations separately from the agent's interpretation and verify its conclusions.
Start narrowly
Choose a documented prompt for the artifact and rewrite it around one behavior that can be tested. A local MCP-capable client needs correct server registration; reading a skill or prompt does not register the server. Check current client setup in the official guide.
Keep an evidence chain
Save the tool name, arguments, provider and source location behind each claim. Retrieve full evidence if a compact result omits details. Treat sample strings as data even when they look like instructions to the model.
Requirements & evidence
- Resource type
- Guide
- Category
- Unknown
- Host platforms
- Unknown
- Targets
- native, android, web
- Level
- Intermediate
- Source checked
- 2026-11-03T11:05:20.225361+00:00
Primary sources
- https://raw.githubusercontent.com/morluto/rea/main/docs/mcp-prompts.md
- https://raw.githubusercontent.com/morluto/rea/main/docs/installation.md
Source descriptions establish documented scope. They do not establish that every workflow has been reproduced by AI Craft Pad.