Terrain
readTerrain
Read Terrain
Read the owner's Terrain - the living map of their fleet in the Agents panel - as JSON, plus everything that has been sculpted onto it.
Ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "what does my terrain look like", and it calls readTerrain.
Example call
The MCP tools/call params, with the required arguments only.
{
"arguments": {},
"name": "readTerrain"
}Arguments
sinceRevisionnumberoptionalReturn `deltas` covering only what has been sculpted AFTER this revision. Omit for the whole terrain with no diff.spacestringoptionalA Space id. Works on that Space's shared terrain layout instead of your own: its members read it, its editors shape it. Omit for your own terrain.
Returns
Returns plots (one per PROJECT, keyed the way the map keys them: repo:owner/name for a repo, project:<id> for a Cloud Project, studio:<id> for a Studio app, and one shared bucket for work…
Declared limits
space: maximum length 128
Ask for it
The Cloud routes these requests to this verb.
- what does my terrain look like
- show me the fleet map
- read the terrain
- which plots are on my map
- what has been sculpted
- what changed on the map since
Pair it with
The verbs that finish the job.
Questions
What does readTerrain do?
Read the owner's Terrain - the living map of their fleet in the Agents panel - as JSON, plus everything that has been sculpted onto it. It is one of the tools The Cloud MCP server gives every connected AI.
How do I use readTerrain from Claude or ChatGPT?
Connect your AI to The Cloud at https://mcp.thecloud.so/mcp and sign in once. Then ask Claude, ChatGPT, Cursor or any AI connected to The Cloud "what does my terrain look like", and it calls readTerrain.
Is readTerrain safe to let an AI call?
readTerrain is read-only: it changes nothing.
Connect
One endpoint gives your AI this tool and every other one: connect Claude, ChatGPT, Cursor or Gemini, read what The Cloud is, or see pricing.