Human visual review for agent-built HTML: publish artifacts, pull anchored comments, push fixes.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Give your agent a place to show its work to humans. Terrarium hosts the HTML your agent builds; humans review it in the browser with comments anchored to exact passages; the agent pulls that feedback over MCP, pushes fixes, and repeats until approved.
Then mint a token at tryterrarium.com/connect
and make it available as TERRARIUM_PAT:
(Or just ask your agent to set Terrarium up β the bundled skill walks it through the whole flow, including sending you to /connect for the token.)
.mcp.json) β Terrarium's remote server over Streamable
HTTP with 7 tools: list_artifacts, publish_artifact, get_artifact,
pull_comments, push_version, reply_to_comment, resolve_comment.skills/terrarium/) β teaches the publish β review β fix loop,
including the terrarium-feedback/1 payload, expectedVersion freshness,
and comment-thread etiquette.pull_comments returns a versioned, structured payload
(terrarium-feedback/1) designed to be stable enough to build agents against:
review state, typed comment threads (change_request / question / bug),
text anchors with live resolution status, and reply chains. Evolution within
/1 is additive-only.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/terrarium-2)<a href="https://allmcps.com/mcp/terrarium-2"><img src="https://allmcps.com/api/badge/terrarium-2?style=directory" alt="Terrarium on AllMCPs" /></a>