io.github.wiserautomation/suprawall-mcp MCP Server

SupraWall is an MCP server described as a “deterministic security layer” for AI agents. It acts as a security gateway that provides strict business policy enforcement and forensic-grade threat detection before an agentic action reaches an API. The repository is positioned as a monorepo of “SupraWall Plugins.”

🛠️ Key Features

Deterministic guardrails for MCP agents
Zero-knowledge, deterministic security layer
Strict business policy enforcement
Forensic-grade threat detection
Prevents agentic action from reaching an API

🚀 Use Cases

Securing agentic workflows that use MCP
Adding AI agent security and guardrails in production systems
Mitigating prompt-injection and improving PII safety

⚡ Developer Benefits

Enforces strict policies rather than probabilistic security models
Interposes security checks between LLMs and production APIs
Supports ecosystems and tooling referenced by topics (e.g., LangChain, MCP)

⚠️ Limitations

No additional operational details (e.g., specific protocols, configuration options, or supported tooling beyond the description) are provided in the source data.

🛡️ SupraWall Plugins Monorepo

The Industry-Standard Deterministic Security Layer for AI Agents.

SupraWall solves the "trust" problem in generative AI by providing a zero-knowledge, deterministic security layer between LLMs and your production systems. Unlike probabilistic security models, SupraWall enforces strict business policies and forensic-grade threat detection before an agentic action even reaches your API.

Official Website | Main Repository | Documentation

🏛️ Project Vision

SupraWall (formerly AgentGate) was built to bridge the gap between high-velocity AI experimentation and enterprise security compliance. Our goal is to empower developers to ship autonomous agentic fleets without the risk of Prompt Injection, PII data leakage, or uncontrolled tool execution.

This monorepo serves as the official distribution hub for all SupraWall plugins and framework integrations.

📦 Plugin Directory

Dify Plugin: Explicit security guardrails for Dify Workflows.
MCP Claude Server: Official implementation of the Model Context Protocol (MCP).
AWS Marketplace Integration: Pre-certified Guardrail tool for AWS Cloud (SaaS & Container).
OpenClaw Extension: Native security middleware for the OpenClaw agent runtime.

🧱 Framework Security Middleware

Seamless "Zero-Trust" wrappers for the industry's leading AI agent frameworks:

AutoGen Integration: Secure protection for Microsoft AutoGen multi-agent topologies.
CrewAI Integration: Deterministic policy enforcement for CrewAI processes and agents.
LangChain (Python & TS): Security interceptors for LangChain chains, tools, and executors.
LlamaIndex Integration: Secure guardrails for RAG pipelines and tool-based retrieval.
Vercel AI SDK Integration: One-line security additions for projects built on the Vercel AI SDK.

🚦 Quick Start

For Dify Marketplace Users

We represent the most robust security option on the Dify Marketplace. To install manually during the initial review phase, use the pre-packaged .difypkg found in the suprawall-security directory.

For Claude Desktop Users

Add SupraWall to your claude_desktop_config.json:

json

{
  "mcpServers": {
    "suprawall": {
      "command": "npx",
      "args": ["-y", "@suprawall/mcp-plugin"]
    }
  }
}

🛡️ Security Architecture

SupraWall is built on three core pillars:

Detection: Real-time identification of adversarial intent (Prompt Injection, SQLi, Jailbreaks).
Scrubbing: Automatic removal of PII (Names, Emails, Keys) before data leaves your environment.
Enforcement: Strict policy-based execution—if a tool call doesn't match your rule, it's blocked.

📄 License

Licensed under the Apache License 2.0.

io.github.wiserautomation/suprawall-mcp