agent-godmode runs on your own machine — the client starts it, so there is no endpoint to ping. 270 installs a week from pypi. Last commit 20 May 2026.
Sandboxed workspace MCP: file ops, argv-only run_command, list_files; BYO LLM prompts.
We read the source, 2 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.
proc = subprocess.run(
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.
proc = subprocess.run(
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 agent-godmode -- uvx agent-godmode
{
"mcpServers": {
"agent-godmode": {
"command": "uvx",
"args": [
"agent-godmode"
]
}
}
}
[mcp_servers.agent-godmode]
command = "uvx"
args = ["agent-godmode"]
{
"mcpServers": {
"agent-godmode": {
"command": "uvx",
"args": [
"agent-godmode"
]
}
}
}
{
"servers": {
"agent-godmode": {
"type": "stdio",
"command": "uvx",
"args": [
"agent-godmode"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
AGENT_GODMODE_ROOT (Absolute workspace root; only paths under this directory are allowed. Omit if you pass --root to the CLI).
Self-hosted MCP server: run OpenAI Codex CLI prompts and manage workspace files.
Give your agent a persistent workspace: files, a code sandbox and a public URL to publish to.
A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.
Linux microVM sandboxes for AI agents: run commands, files, processes, pause and wake.
Persistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.
Safe Google Workspace admin for AI agents: read-only by default, confirm-gated deletes, audit log.
Governed skills, rules and commands for AI coding agents, served by a read-only MCP server.
Read-only catalog of prompt packs and rule files: Cursor, CLAUDE.md, AGENTS.md, SKILL.md.
Answers built from our own checks of this server.