🛡️ Ultra-fast local security firewall, secret sanitizer, and context token compressor for Claude Code, Cursor, and MCP AI agents.
The local privacy firewall, prompt-injection shield, secret sanitizer, and token compressor for AI coding agents.
A zero-dependency security proxy for Model Context Protocol (MCP) servers.
mcp-guard is an ultra-fast, zero-dependency Go binary that sits transparently between your editor (Claude Code, Cursor, VS Code, Copilot) and any Model Context Protocol (MCP) server — over stdio or HTTP/SSE.
It ensures your API keys, database credentials, and protected paths (~/.ssh, .env, .git) are never leaked to cloud LLMs, that malicious content cannot hijack your agent, and that autonomous tool execution cannot touch what it shouldn't — all while trimming token spend.
When AI agents run tools like @modelcontextprotocol/server-filesystem or postgres-mcp, they read raw files and query results straight off your machine. Three things go wrong:
1. Secrets leak. A file with AWS keys, JWTs, or DB passwords gets shipped verbatim to a cloud LLM. 2. Agents get hijacked. A file or web page can carry hidden instructions — invisible Unicode or "ignore all previous instructions" — that the model obeys (prompt injection / tool poisoning). 3. Agents overreach. An autonomous agent overwrites ~/.ssh/authorizedkeys, pipes curl … bash, or reads 100 files in a burst.
mcp-guard runs locally and fixes all three without breaking agent execution:
- 🔒 Zero-Trust I/O Inspection — intercepts both requests and responses on every transport. - ⚡ Zero-Dependency Go Binary — pure standard library, sub-millisecond overhead. - 🔄 Recoverable Guardrail Errors — returns structured isError: true results so agents s
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/sainitish1609--mcp-guard.html)
Keep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
slxca/opencontextA Model Context Protocol server for persistent project-specific AI agent context.
dontpayfull/AInotateAnnotated screenshots for AI agents: Skitch-style arrows, numbered steps, boxes, labels, solid redaction
replenhq/replenSmarter AI Development Workflows
menot-you/n-memoryMemory your agent can trust — every answer carries its source; when it doesn't know, it says so. Hermetic, local, MCP.
limoaCatherine/game-studio-harnessDeployable Cursor game-studio harness: rules, skills, crafts, and MCP wiring. 可部署的游戏工作室 Harness：规则、技能、工艺与 MCP 接线。不含工作室数据、密钥或 DCC 程序。
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.