mcpbeat Sign in

Sidclaw Governance MCP Server

local only

Sidclaw Governance MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 39 installs a week from npm. Last commit 29 Jul 2026.

Governance proxy for MCP servers — policy evaluation, human approval, audit trails.

Installs per day peak 27 · avg 10 · +52% w/w
a month agotoday
39
Installs / week
npm · @sidclaw/sdk
14
Stars
1 open issues
29 Jul 2026
Last commit
0 releases in 90 days
Apache-2.0
License
TypeScript

What the code does

We read the source, 19 h ago · rules 3dff92dd89df

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.

File ships in the package but is absent from the source [пакет] bin/sidclaw-mcp-proxy.cjs:1
этот файл ставится пользователю, но в репозитории его нет
Runs an external command packages/sidclaw-demo/cli.mjs:36
    const child = spawn(opener[0], opener[1], { detached: true, stdio: 'ignore' });
Sends data to a third-party sink apps/api/src/routes/integrations/telegram.ts:136
  await fetch(`https://api.telegram.org/bot${botToken}/answerCallbackQuery`, {
Secret passed into the image build apps/landing/Dockerfile:23
ENV NEXT_PUBLIC_CF_BEACON_TOKEN=$NEXT_PUBLIC_CF_BEACON_TOKEN
Touches key and credential files hooks/sidclaw_agent_intel/bash_classifier.py:141
    ("/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.

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

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.

run in your terminal
claude mcp add sidclaw-governance-mcp -- npx -y @sidclaw/sdk
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "sidclaw-governance-mcp": {
      "args": [
        "-y",
        "@sidclaw/sdk"
      ],
      "command": "npx"
    }
  }
}
~/.codex/config.toml
[mcp_servers.sidclaw-governance-mcp]
command = "npx"
args = ["-y", "@sidclaw/sdk"]
.cursor/mcp.json
{
  "mcpServers": {
    "sidclaw-governance-mcp": {
      "args": [
        "-y",
        "@sidclaw/sdk"
      ],
      "command": "npx"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "sidclaw-governance-mcp": {
      "args": [
        "-y",
        "@sidclaw/sdk"
      ],
      "command": "npx"
    }
  }
}

This one needs environment variables set before it will start: 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), SIDCLAW_APPROVAL_MODE (Approval mode: error (default, returns immediately) or block (waits for approval)). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Sidclaw Governance MCP

same job, measured the same way
mcp-airlock
by shalimov04

Governance proxy for MCP servers: allowlist, forced dry run, human confirmation, blast radius, audit

local only
Sovereign Gateway
by mattijsmoens

Gating proxy for MCP servers: policy, verification and one audit trail across upstreams.

285 installs/wk local only
Mova Flat Runner
by mova-compact

Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.

77 installs/wk local only
Delego
by delego-dev

Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.

202 installs/wk local only
Mastyf AI
by mastyf-ai

Runtime proxy for MCP security, cost governance & audit

72 installs/wk local only
Bulwark
by bpolania

AI agent governance: content scanning, audit logs, policy evaluation, session management.

local only
AgentFabric — Human-in-the-Loop Review & Approval
by enzoduit

Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.

1 tools answering
Aegis — AI Agent Governance
by acacian

Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.

488 installs/wk local only

Sidclaw Governance MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Sidclaw Governance MCP?
Sidclaw Governance MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @sidclaw/sdk was installed 39 times last week.
How do I connect Sidclaw Governance MCP?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls @sidclaw/sdk straight from npm; nothing to host, nothing to sign up for.
How many people use Sidclaw Governance MCP?
The npm package @sidclaw/sdk was installed 39 times in the last week. Week over week that is +52%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Sidclaw Governance MCP open source?
Yes — it is published under the Apache-2.0 licence, written in TypeScript, 14 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.