mcpbeat Sign in

artifact-site MCP Server

not responding

artifact-site is listed as active in the registry but did not answer our last check. 52 installs a week from npm. Last commit 3 Nov 2026.

One place for every AI agent's pages and docs: versioned links to share, search and update.

Installs per day peak 15 · avg 6 · -12% w/w
a month agotoday
Uptime history 46 days of history · worst day 0%
46 days agonow
0.0%
Uptime 24h
0 of 92 checks
—
Tools
hidden behind auth
846 ms
Response time
average over 24h
52
Installs / week
npm and PyPI

What the code does

We read the source, 4 d ago · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

    await new Promise<void>((resolve) => { const p = spawn(cmd, args, { stdio: "ignore", detached: true, shell: false }); p.on("error", () => resolve()); p.unref(); resolve(); });
In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Builds a file path from a variable src/lib/config.ts:11
  return path.isAbsolute(value) ? value : path.join(/* turbopackIgnore: true */ projectRoot, value);
Builds a database query by concatenation src/lib/db-postgres.ts:682, src/lib/directory.ts:89
…d)) OR (s.owner_id IS NULL AND s.anon_owner_id = $2) THEN (SELECT COUNT(*) FROM site_views sv WHERE sv.site_id=s.id) + (SELECT COUNT(*) FROM share_views shv WHERE shv.site_id=s.id) + COALESCE((SELECT opens FROM archived_view_counts av WHERE av.site_id=s.id), 0) END AS total_views…

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 1 min ago.

run in your terminal
claude mcp add artifact-site --transport http https://artifact-site.app.lexmount.com/mcp
Settings → Connectors → Add custom connector, then paste this address
https://artifact-site.app.lexmount.com/mcp
~/.codex/config.toml
[mcp_servers.artifact-site]
url = "https://artifact-site.app.lexmount.com/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "artifact-site": {
      "url": "https://artifact-site.app.lexmount.com/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "artifact-site": {
      "type": "http",
      "url": "https://artifact-site.app.lexmount.com/mcp"
    }
  }
}

Endpoints

URLTransportStateLatencyChecked
https://artifact-site.app.lexmount.com/mcp streamable-http answering 846 ms 1 min ago

Alternatives to artifact-site

same job, measured the same way
Artfct
by artfct

Shared workspace for AI artifacts: your agents publish, search and cite each other's work.

answering
Writespace MCP
by write-space

Persistent docs and memory for AI agents — read, write, organize & search a shared workspace.

answering
A
AgentDrive
by tokencanopy

Artifact store for AI agents — read, write, and search files by path; share by rendered URL.

answering
Mem0
by mem0ai

Persistent memory for AI agents: add, search, update, and delete long-term memories.

answering
memsprout
by memsprout

shared AI-context layer for teams — persistent memory your agents search and update over MCP

answering
Evergences Shared Memory
by seanmeverett

Public source-linked memories for AI agents: search, read, cite, reply, and share findings.

local only
Knowngood
by knowngood

Search agent-ready sites or fetch one site's report; every capability probe-verified, dated.

3 tools answering
sayou
by pixell-global

Persistent knowledge workspace for AI agents. Versioned files, search, and MCP tools.

69 installs/wk local only

artifact-site — questions

Answers built from our own checks of this server.

Is artifact-site working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 92 checks got a reply (0.0%), average response time 846 ms. The bar chart above shows every period we have measured.
The registry lists artifact-site as active — why does it not respond?
The official MCP registry stores what the author submitted; it does not verify that the server still runs. We check the endpoint ourselves, and this one does not answer. Catalogues that copy the registry without checking will show it as working.
How do I connect artifact-site?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does artifact-site need an API key?
No. artifact-site completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. This is what we observed, not what the docs claim.
How many people use artifact-site?
The npm package @artifact-site/cli was installed 52 times in the last week. Week over week that is -12%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is artifact-site open source?
The code is open source: it is published under the Apache-2.0 licence, written in TypeScript and 26 stars on GitHub. The licence covers the code in the repository, not the hosted service at artifact-site.app.lexmount.com, which runs on its operator's own terms.