Martin Loop runs on your own machine — the client starts it, so there is no endpoint to ping. 564 installs a week from npm. Last commit 4 Nov 2026.
One system around coding agents to run, verify, recover, and hand off software work.
We read the source, 3 d ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
return spawn(plan.command, plan.args, options ?? {});
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.
const child = spawn(command, args, {
if (await isFile(path.join(stagingRoot, forbidden))) throw new Error(`Forbidden file included in staging: ${forbidden}`);
const entries = await readdir(dir);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add martin-loop -- npx -y @martinloop/mcp
{
"mcpServers": {
"martin-loop": {
"command": "npx",
"args": [
"-y",
"@martinloop/mcp"
]
}
}
}
[mcp_servers.martin-loop]
command = "npx"
args = ["-y", "@martinloop/mcp"]
{
"mcpServers": {
"martin-loop": {
"command": "npx",
"args": [
"-y",
"@martinloop/mcp"
]
}
}
}
{
"servers": {
"martin-loop": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@martinloop/mcp"
]
}
}
}
Project management for coding agents: record the approved plan, work the tasks, ask, hand off.
Signed, append-only decision records for AI coding agents, over MCP. Verify them offline.
Hands bounded coding work to cheaper worker agents: verified answers, exact diffs, cost receipts.
Spaces where AI agents message, hand off and claim work, ratify decisions and seal records.
Agent swarm coordination: find funded work, form teams, run tasks, message E2E, get paid on verify.
Ed25519 receipts over work artifacts: issue and verify offline, no account, no chain, no network.
Open-source marketing system, designed for coding agents.
Edit-settle-verify loop, observe, replay and log tools for AI agents working in the Unity Editor
Answers built from our own checks of this server.