Sidclaw Governance MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 67 installs a week from npm. Last commit 25 Sep 2026.
Governance proxy for MCP servers — policy evaluation, human approval, audit trails.
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.
const child = spawn(opener[0], opener[1], { detached: true, stdio: 'ignore' });
await fetch(`https://api.telegram.org/bot${botToken}/answerCallbackQuery`, {
ENV NEXT_PUBLIC_CF_BEACON_TOKEN=$NEXT_PUBLIC_CF_BEACON_TOKEN
("/etc/shadow", re.compile(r"/etc/shadow\b")),
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 Sidclaw Governance MCP 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 sidclaw-governance-mcp -e 'SIDCLAW_API_KEY=<SIDCLAW_API_KEY>' -e 'SIDCLAW_AGENT_ID=<SIDCLAW_AGENT_ID>' -e 'SIDCLAW_UPSTREAM_CMD=<SIDCLAW_UPSTREAM_CMD>' -e 'SIDCLAW_UPSTREAM_ARGS=<SIDCLAW_UPSTREAM_ARGS>' -- npx -y @sidclaw/sdk{
"mcpServers": {
"sidclaw-governance-mcp": {
"command": "npx",
"args": [
"-y",
"@sidclaw/sdk"
],
"env": {
"SIDCLAW_AGENT_ID": "<SIDCLAW_AGENT_ID>",
"SIDCLAW_API_KEY": "<SIDCLAW_API_KEY>",
"SIDCLAW_UPSTREAM_ARGS": "<SIDCLAW_UPSTREAM_ARGS>",
"SIDCLAW_UPSTREAM_CMD": "<SIDCLAW_UPSTREAM_CMD>"
}
}
}
}[mcp_servers.sidclaw-governance-mcp]
command = "npx"
args = ["-y", "@sidclaw/sdk"]
env = { SIDCLAW_API_KEY = "<SIDCLAW_API_KEY>", SIDCLAW_AGENT_ID = "<SIDCLAW_AGENT_ID>", SIDCLAW_UPSTREAM_CMD = "<SIDCLAW_UPSTREAM_CMD>", SIDCLAW_UPSTREAM_ARGS = "<SIDCLAW_UPSTREAM_ARGS>" }{
"mcpServers": {
"sidclaw-governance-mcp": {
"command": "npx",
"args": [
"-y",
"@sidclaw/sdk"
],
"env": {
"SIDCLAW_AGENT_ID": "<SIDCLAW_AGENT_ID>",
"SIDCLAW_API_KEY": "<SIDCLAW_API_KEY>",
"SIDCLAW_UPSTREAM_ARGS": "<SIDCLAW_UPSTREAM_ARGS>",
"SIDCLAW_UPSTREAM_CMD": "<SIDCLAW_UPSTREAM_CMD>"
}
}
}
}{
"servers": {
"sidclaw-governance-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sidclaw/sdk"
],
"env": {
"SIDCLAW_AGENT_ID": "<SIDCLAW_AGENT_ID>",
"SIDCLAW_API_KEY": "<SIDCLAW_API_KEY>",
"SIDCLAW_UPSTREAM_ARGS": "<SIDCLAW_UPSTREAM_ARGS>",
"SIDCLAW_UPSTREAM_CMD": "<SIDCLAW_UPSTREAM_CMD>"
}
}
}
}Put your own values in place of
<SIDCLAW_API_KEY> (SidClaw API key for policy evaluation and audit logging), <SIDCLAW_AGENT_ID> (Agent identity for policy matching and audit trails), <SIDCLAW_UPSTREAM_CMD> (Command for the upstream MCP server (e.g., npx)), <SIDCLAW_UPSTREAM_ARGS> (Comma-separated args for the upstream MCP server).
The author’s registry entry marks them as required.
Optional settings from the registry entry, left out of the block above:
SIDCLAW_APPROVAL_MODE (Approval mode: error (default, returns immediately) or block (waits for approval)).
Alternatives to Sidclaw Governance MCP
same job, measured the same wayGovernance proxy for MCP servers: allowlist, forced dry run, human confirmation, blast radius, audit
Gating proxy for MCP servers: policy, verification and one audit trail across upstreams.
Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.
Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.
Runtime proxy for MCP security, cost governance & audit
AI agent governance: content scanning, audit logs, policy evaluation, session management.
Local stdio MCP server for the AEGIS governance client. The hosted evaluation service is offline.
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Sidclaw Governance MCP — questions
Answers built from our own checks of this server.