Terrarium

io.github.nelsonsantryhkdPublished by GitHub account nelsonsantryhkdv0.1.0Updated Oct 25, 2026

Human visual review for agent-built HTML: publish artifacts, pull anchored comments, push fixes.

VerifiedStreamable HTTPWeb executableDeveloper ToolsCommunication & Collaboration

Overview

AI-generated overview

Terrarium hosts HTML artifacts your agent builds and lets humans review them in the browser, with the agent pulling anchored comments and pushing fixes over MCP

What you can do
List and publish HTML artifacts, and fetch a specific artifact's details and current version state. Pull structured review feedback with typed comment threads, text anchors and reply chains. Push new versions of an artifact after making fixes. Reply to comments and mark comments resolved to close the review loop.
When to use it
Useful when an agent produces HTML pages or reports that a person should review before they are final, and you want the feedback to come back to the agent as structured, anchored comments rather than loose chat messages.
Requirements
A remote Streamable HTTP endpoint at tryterrarium.com, reachable over the network. OAuth authentication with an Authorization header carrying a bearer personal access token, which the README says is minted at the provider's connect page and supplied as TERRARIUM_PAT. A Terrarium account is implied.
Before you install
The Authorization header carries a personal access token, so treat it as a secret and avoid exposing it in logs or shared configs. The server publishes artifacts and pushes versions, replies to comments and resolves comments, all of which change state visible to human reviewers. Artifact content is hosted by a third party.

Installation

In SourceWeft

  1. Open Terrarium in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.nelsonsantryhkd%2Fterrarium/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "terrarium": {
      "type": "http",
      "url": "https://www.tryterrarium.com/api/mcp"
    }
  }
}

README

Terrarium plugin for Claude Code

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.

Install

/plugin marketplace add nelsonsantryhkd/terrarium-plugin/plugin install terrarium@terrarium

Then mint a token at tryterrarium.com/connect and make it available as TERRARIUM_PAT:

sh
export TERRARIUM_PAT="samus_pat_…"

(Or just ask your agent to set Terrarium up — the bundled skill walks it through the whole flow, including sending you to /connect for the token.)

What it ships

  • MCP server (.mcp.json) — 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.
  • Skill (skills/terrarium/) — teaches the publish → review → fix loop, including the terrarium-feedback/1 payload, expectedVersion freshness, and comment-thread etiquette.

The protocol

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.

Source: README.md at commit 25730a8

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.