MCPower Security Proxy
- 3 repo stars
- Updated December 22, 2025
- MCPower-Security/mcpower-proxy
MCPower Security Proxy is a MCP server that wraps other MCP servers with real-time monitoring and policy enforcement.
About
MCPower Security Proxy is a Model Context Protocol server that sits in front of other MCP servers and adds security-oriented wrapping, live monitoring, and policy enforcement. developers who chain many community MCP tools into Claude Code or Cursor often lack a single choke point for what an agent is allowed to call; this proxy is meant to be that layer without replacing each upstream server. You install it as a PyPI stdio server (identifier mcpower-proxy, version 0.0.91) and point your client at the proxied endpoints rather than raw integrations. It is best when you are shipping agent features that touch sensitive APIs, filesystem paths, or paid third-party tools and you want observability plus rules before users see the product. It is not a full IAM platform or code scanner—it governs the MCP channel specifically. Pair it with secret hygiene and review skills; expect intermediate setup comfort with MCP config and environment wiring.
- Automatically proxies and wraps existing MCP servers without rewriting each integration
- Real-time monitoring of MCP traffic and tool invocations
- Policy enforcement layer on top of stdio MCP workloads
- PyPI package mcpower-proxy (v0.0.91) with uvx runtime hint
- stdio transport suitable for Claude Code, Cursor, and other MCP clients
MCPower Security Proxy by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add mcpower-proxy -- uvx mcpower-proxyAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| repo stars | ★ 3 |
|---|---|
| Package | mcpower-proxy |
| Transport | STDIO |
| Auth | None |
| Last updated | December 22, 2025 |
| Repository | MCPower-Security/mcpower-proxy ↗ |
What it does
Wrap arbitrary MCP servers behind monitoring and enforced policies so your coding agent cannot bypass guardrails.
Who is it for?
Best when you're shipping MCP-heavy agents and need a guardrail layer before exposing integrations to customers or teammates.
Skip if: Skip if you only use built-in IDE tools with no MCP chain, or anyone expecting full app penetration testing from this package alone.
What you get
After registration, upstream MCP servers run behind a monitored, policy-aware proxy your agent talks to instead of calling tools directly.
- Proxied MCP endpoints with monitoring enabled
- Policy-enforced tool access path for your agent
- Observable MCP invocation trail for ship and operate reviews
By the numbers
- Server schema version 0.0.91 on PyPI identifier mcpower-proxy
- stdio transport with uvx runtime hint
- Source repository: github.com/MCPower-Security/mcpower-proxy
README.md
Defenter
Real-time semantic security for AI coding agents and MCP tools in VS Code, Claude Code and Cursor.
Defenter monitors every prompt, every coding agent tool call, every MCP server call, and key file and shell operations in your IDE. It acts as a semantic policy broker that understands what agents are doing, not just where they send data, so you can use AI coding agents without leaking secrets or customer data.
🚀 How to use
The simplest way to use Defenter is to install the VS Code or Cursor extension:
- VS Code Marketplace: Install Defenter
- Open VSX (Cursor and others): Install Defenter
- Claude Code: install Defenter plugin
Once installed, the extension automatically intercepts and protects:
- MCP server calls
- Coding agent prompts and responses
- File reads and shell commands triggered by the agent
No manual MCP configuration is needed.
Overview
Defenter is a semantic policy broker for AI coding agents. It adds an intelligent security layer inside your IDE that:
- Intercepts every coding agent prompt and action
- Wraps every MCP tool call and response
- Analyzes the payload for sensitive information and risky behavior in real time
- Enforces your security policies with allow, redact, or block decisions
Traditional security tools cannot see what an agent is about to share or execute. They look at apps and destinations, not at the intent and content of an agent’s actions.
Defenter bridges this gap by:
- Preventing data leaks and context contamination
- Providing clear, visual monitoring of every agent decision
Architecture and how it works
This repository contains the Defenter proxy and related components that secure MCP and coding agent traffic.
Defenter is built as a Python based proxy and local middleware that the IDE extension uses to enforce policy. At a high level:
Local middleware layer
- Runs on the developer machine
- Hooks coding agent prompts, file reads, and shell executions
- Intercepts all MCP tool calls and responses
- Performs client side redaction of secrets and PII
Cloud powered policy engine
- Receives a minimal, redacted payload
- Uses a classifier and analyzer to check for data leaks, context contamination, and prompt injection
- Returns Allow, Redact, Need more info, or Block decisions in real time
- Works with low latency to make sure the development flow in without friction
IDE integration
- Seamless integration with VS Code and Cursor extensions
- Shows a live monitoring view of all agent actions and Defenter decisions directly inside the IDE
Together, these pieces let you harness AI coding agents and MCP tools without compromising the security of your code, data, or workflows.
References
Python Proxy: See src/README.md for detailed implementation documentation
VSC Extension: See targets/vsc-extension/README.md for installation and user guide
Recommended MCP Servers
1Claw VaultHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.2
1passwordMCP server for 1Password service accounts — tools and resources for vaults and credentials18
402sentinel McpAssess an x402 counterparty's risk BEFORE paying: allow/review/block, scored on-chain (Base).1
A2adependencyinspector McpRemote MCP for A2A dependency inspector MCP, structured receipts, audit logs, and reviewer-ready evi
A2a Governance Bridge McpA2A Governance Bridge MCP server.A2aidentitytoll McpRemote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.How it compares
MCP security proxy and policy wrapper, not a standalone agent skill or vulnerability scanner.
FAQ
Who is MCPower Security Proxy for?
and small-team developers who run multiple MCP servers with Claude Code, Cursor, or similar clients and want centralized monitoring and enforcement.
When should I use MCPower Security Proxy?
Use it when you are integrating third-party or custom MCP tools and need to ship or operate with clearer boundaries and live visibility on tool usage.
How do I add MCPower Security Proxy to my agent?
Register the PyPI package mcpower-proxy (stdio, uvx hint) in your MCP client config and route target servers through the proxy per the GitHub MCPower-Security/mcpower-proxy README.