Governance Proxy
Verified IntegrationClient Configuration
— Connect Governance Proxy to Claude Desktop or Cursor in seconds{
"mcpServers": {
"governance-proxy": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-governance-proxy"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Evaluates every AI agent tool call before execution, holding risky actions for human review to ensure secure interaction with real systems.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Governance Proxy
Yes, Governance Proxy supports pluggable policy evaluators. You can use an allow-list, integrate with continuous risk scoring engines like Wave Engine, or implement your own custom Python logic to define nuanced rules for auto-execution, holding for review, or blocking agent actions.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.