Dashclaw runs on your own machine — the client starts it, so there is no endpoint to ping. 110 installs a week from npm. Last commit 1 Oct 2026.
Policy checks, approvals, records, and governed HTTP capabilities for unattended agents.
What the code does
We read the source, 3 d ago · rules 995398eba69f
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.
rm -rf'd a node_modules I actually needed for a different
env_path = os.path.join(current, fname)
subprocess.run(
execFile(
shell=True,
"secrets": ["**/secrets/**", "**/.env", "**/.env.*", "**/*.pem", "**/id_rsa*", "**/*.key", "app/secrets/**"],
const TELEGRAM_API_BASE = 'https://api.telegram.org';
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Nothing serious here today
Today is the operative word: we check Dashclaw every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Connect this server
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 dashclaw -e 'DASHCLAW_URL=<DASHCLAW_URL>' -e 'DASHCLAW_API_KEY=<DASHCLAW_API_KEY>' -- npx -y @dashclaw/mcp-server{
"mcpServers": {
"dashclaw": {
"command": "npx",
"args": [
"-y",
"@dashclaw/mcp-server"
],
"env": {
"DASHCLAW_API_KEY": "<DASHCLAW_API_KEY>",
"DASHCLAW_URL": "<DASHCLAW_URL>"
}
}
}
}[mcp_servers.dashclaw]
command = "npx"
args = ["-y", "@dashclaw/mcp-server"]
env = { DASHCLAW_URL = "<DASHCLAW_URL>", DASHCLAW_API_KEY = "<DASHCLAW_API_KEY>" }{
"mcpServers": {
"dashclaw": {
"command": "npx",
"args": [
"-y",
"@dashclaw/mcp-server"
],
"env": {
"DASHCLAW_API_KEY": "<DASHCLAW_API_KEY>",
"DASHCLAW_URL": "<DASHCLAW_URL>"
}
}
}
}{
"servers": {
"dashclaw": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@dashclaw/mcp-server"
],
"env": {
"DASHCLAW_API_KEY": "<DASHCLAW_API_KEY>",
"DASHCLAW_URL": "<DASHCLAW_URL>"
}
}
}
}Put your own values in place of
<DASHCLAW_URL> (Base URL of your DashClaw instance (e.g. https://your-app.vercel.app)), <DASHCLAW_API_KEY> (DashClaw workspace API key (oc_live_...)).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
DASHCLAW_AGENT_ID (Optional agent identifier used to attribute governed actions).
Alternatives to Dashclaw
same job, measured the same wayGoverned MCP gateway: approved tools only, each call policy-checked and recorded per agent
Governed execution cells for AI agents: Docker/K8s sandboxes with policy, audit, and approvals.
Governed USDC wallet for AI agents — policy gates, spending caps, and Ed25519-signed receipts.
Agent-native MCP for governed commerce, x402 payments, paid capabilities, and verifiable receipts.
Watchdog for unattended AI agents: alerts, evidence checks and a verifiable proof per run.
Trust OS for AI agents: governed memory, payments, reputation, approvals, and audit evidence.
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
Find and run governed Excel model capabilities that your organisation has published for AI agents.
Dashclaw — questions
Answers built from our own checks of this server.