mcpbeat Sign in

Headmesh Agent Sandbox MCP Server

by headmesh-dev Your server? Claim it
not responding

Headmesh Agent Sandbox is listed as active in the registry but did not answer our last check. Last commit 5 Nov 2026.

Run commands, edit files and manage Git and persistent sessions in your own isolated sandbox.

Uptime history 67 hours of history · worst hour 0%
67 hours agonow
0.0%
Uptime 24h
0 of 91 checks
—
Tools
hidden behind auth
2 ms
Response time
average over 24h
0
Stars
last commit 5 Nov 2026

What the code does

We read the source, 1 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.

    if err := os.Rename(tmp, filepath.Join(a.cfg.StateDir, name)); err != nil {
Builds a database query by concatenation core/cellagent/runner.go:77
        select {
        case <-ctx.Done():
        case <-time.After(backoff/2 + jitter):
Page loads a third-party script web/marketing/src/pages/waitlist.astro:133
  <script is:inline src="https://challenges.cloudflare.com/turnstile/v0/api.js" async defer></script>
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.

  for _ in $(seq 1 30); do runuser -u postgres -- pg_isready -q && return 0; sleep 1; done
Asks for container control access .github/workflows/sandbox-image.yml:77
          docker run --rm -v /var/run/docker.sock:/var/run/docker.sock:ro \
Touches key and credential files deploy/compose/bootstrap.sh:95, deploy/deploy.sh:132
  [[ -s /root/.ssh/authorized_keys ]] || die "/root/.ssh/authorized_keys is empty"

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 9 min ago.

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

Endpoints

URLTransportStateLatencyChecked
https://{sandbox_host}/mcp streamable-http answering 2 ms 9 min ago

Alternatives to Headmesh Agent Sandbox

same job, measured the same way
Cdbx
by cdbx

Build Apps and run code in 30 languages — sandboxed, with persistent sessions for agent loops.

answering
Shardflux
by shardflux

Persistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.

669 installs/wk answering
LetKite
by letkite

Run commands and manage files on your own machines. Needs a LetKite account; OAuth sign-in.

answering
AgentSpace
by com-agentspace

Give your agent a persistent workspace: files, a code sandbox and a public URL to publish to.

answering
Airlox
by claudezss

Run your coding agent's commands on machines you own: a sandboxed job slot, not an SSH login.

972 installs/wk local only
Command Mail
by commandmail

One inbox for all your addresses: your AI agent reads, sorts, drafts and sends with your permission.

answering
Marsell
by marsell-official

Manage content, marketing and sales in Marsell with your own AI. Read work and act with permission.

125 tools answering
Marsell
by getmarsell

Manage content, marketing and sales in Marsell with your own AI. Read work and act with permission.

125 tools answering

Headmesh Agent Sandbox — questions

Answers built from our own checks of this server.

Is Headmesh Agent Sandbox working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 0 of 91 checks got a reply (0.0%), average response time 2 ms. The bar chart above shows every period we have measured.
The registry lists Headmesh Agent Sandbox 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 Headmesh Agent Sandbox?
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 Headmesh Agent Sandbox need an API key?
No. Headmesh Agent Sandbox 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.
Is Headmesh Agent Sandbox open source?
The code is open source: it is published under the Apache-2.0 licence, written in Go and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service, which runs on its operator's own terms.