MCPower Security Proxy
- 3 repo stars
- Updated December 22, 2025
- MCPower-Security/mcpower-proxy
io.github.ai-mcpower/mcpower-proxy is a MCP server that wraps other MCP servers with real-time monitoring and policy enforcement.
About
MCPower Security Proxy is an MCP server that sits in front of other MCP servers to add real-time monitoring and policy enforcement. For developers who already run several MCP integrations in Claude Code or Cursor, it reduces the blast radius when an agent mis-invokes a tool or a compromised package exfiltrates data. You typically run it with uvx from PyPI over stdio, configuring it to proxy your underlying servers rather than replacing them outright. It is an infrastructure-style MCP component—not a skill that teaches secure coding—and it pairs well with least-privilege API keys and manual review before launch. Version 0.0.87 indicates active iteration; treat policies as code, test in a sandbox project, then promote the same proxy layout to production agent setups.
- Wraps upstream MCP servers as a security proxy layer
- Real-time monitoring of MCP server activity
- Policy enforcement on tool and resource access
- Stdio transport via uvx/PyPI mcpower-proxy (v0.0.87)
- Official MCPower Security Proxy branding in registry metadata
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 existing MCP servers behind a security proxy that monitors traffic and enforces policies in real time.
Who is it for?
Best when you're running multiple MCP tools and want a single choke point for monitoring and enforcement without rewriting each server.
Skip if: Anyone with only one trivial MCP server and no sensitive credentials in the toolchain.
What you get
You route MCP traffic through a proxy that watches calls live and blocks or shapes behavior according to your policies.
- Proxied MCP path with monitoring enabled for agent sessions
- Policy rules applied to MCP tool invocations
- Reduced direct exposure of raw upstream MCP endpoints to the agent
By the numbers
- Published version: 0.0.87
- Transport: stdio
- Registry: PyPI identifier mcpower-proxy with runtimeHint uvx
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 gate, not an agent skill or raw third-party API connector.
FAQ
Who is MCPower proxy for?
Developers and small teams using Claude Code or similar hosts who run several MCP servers and need centralized monitoring and policy control.
When should I use MCPower proxy?
Use it in the ship security phase before giving agents broad MCP access to production APIs, secrets, or customer data.
How do I add MCPower proxy to my agent?
Run mcpower-proxy via uvx from PyPI as a stdio MCP entry, configure it to front your upstream MCP servers per MCPower Security docs, then point your agent host at the proxy.