MCP.Market

Terrarium MCP server

online · 100% uptime
by nelsonsantryhkd·io.github.nelsonsantryhkd/terrarium·v0.1.0·2 stars
No reviews yet

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

A92/100grade A
Write a reviewRun it
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

2 stars

Reviews

Write one

Nobody has reviewed Terrarium yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Terrarium tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1010ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityOAuth resource metadata advertised on 40115/15
  • Maintenancelast push 81 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Terrarium compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Uptime
100%
of our recent checks; the typical remote AI and agents server answers 100%
Response time
200 ms
faster than 66% of 2,331 AI and agents servers
GitHub stars
2
more than 65% of 2,711 AI and agents servers

Install Terrarium in Claude Code, Cursor or VS Code

claude mcp add --transport http terrarium https://www.tryterrarium.com/api/mcp
Add to Cursor

What the publisher says

From the Terrarium repository's README, as published. We do not edit it. Read it on GitHub

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:

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

HTTP with 7 tools: listartifacts, publishartifact, getartifact, pullcomments, pushversion, replytocomment, resolvecomment.

  • MCP server (.mcp.json) — Terrarium's remote server over Streamable

including the terrarium-feedback/1 payload, expectedVersion freshness, and comment-thread etiquette.

  • Skill (skills/terrarium/) — teaches the publish → review → fix loop,

The protocol

pullcomments returns a versioned, structured payload (terrarium-feedback/1) designed to be stable enough to build agents against: review state, typed comment threads (changerequest / question / bug), text anchors with live resolution status, and reply chains. Evolution within /1 is additive-only.

Nothing above is checked by us. What we check is on the safety report.

Terrarium: common questions

Is Terrarium MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Terrarium safety report
How do I install Terrarium?
It runs remotely at www.tryterrarium.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Terrarium need an API key?
No key to paste: it signs you in with OAuth when your client connects.
Is Terrarium maintained?
The last commit was 120 days ago (2026-07-07). The latest release is v0.1.0.
Is Terrarium up?
100% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Terrarium?
Servers from other publishers that do the same job: Maple MCP server, Agent-Native Plan MCP server and OpenWorkProof MCP server.
How does Terrarium compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); uptime 100% (of our recent checks; the typical remote AI and agents server answers 100%); response time 200 ms (faster than 66% of 2,331 AI and agents servers). Full comparison.

Alternatives to Terrarium

Same job from other publishers: the closest match first, then the best rated.

  • Maple
    Review comments pinned to a running frontend, read and resolved by your coding agent.
    B
  • Agent-Native Plan
    Structured visual plans and PR recaps with diagrams, prototypes, annotations, and sharing
    More from BuilderIO →
    A
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A
  • Superlog
    Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents.
    A
  • CHAP Coordinator
    Auditable records of human decisions over AI agent work. Approvals, edits, overrides, escalations.
    A