LLM Prompt Firewall & AI Security Toolkit for Claude, Cursor, and Windsurf
⚡ AgenticStore MCP Server: LLM Prompt Firewall & AI Security Toolkit
Open-Source Model Context Protocol (MCP) Server for Data Privacy, Prompt Recording, Audit Logs, and 27+ Agent Tools for Claude, Cursor, and Windsurf.
🚀 Quick Start • 🛡️ Prompt Firewall • 🗂️ Full Tool Directory • 🌐 Web Search • 🔌 Client Setup • 🖥️ GUI Webapp
🔒 Why You Need This: Enterprise-Grade AI Security Meets Autonomous Agents
Giving AI assistants like Claude, Cursor, and Windsurf access to your codebase and the web is a superpower. But passing sensitive enterprise data to remote LLMs is a massive security risk.
The Problem: You want the massive productivity boost of agentic workflows, but you cannot compromise on Data Loss Prevention (DLP), compliance, or leak prevention.
The Solution: AgenticStore MCP Server solves both halves of the equation:
- 🛡️ The LLM Prompt Firewall: A secure local proxy that intercepts, scans, and sanitizes your prompts before they leave your machine. It flags leaked secrets, PII, and API keys, using local models (like Ollama) to sanitize data and generate strict audit traces for all AI usage.
- 🧰 The MCP Toolkit: A robust, production-ready arsenal of 27 tools. Instantly arm your AI with everything from self-hosted SearXNG web search to deep, persistent semantic memory.
Zero subscriptions. Zero vendor lock-in. Configure your MCP tools manually or effortlessly through a beautiful local GUI.
🎥 Prompt Firewall Demo
(If the video above doesn't load, click here to watch the demo)
🎥 Watch the GUI Demo in Action (MCP Tools)
(If the video above doesn't load, click here to watch the demo)
🏗️ How It Works
🔥 Why Choose AgenticStore MCP?
| Feature | AgenticStore MCP Server | Standard MCP Servers |
|---|---|---|
| AI Security & Prompt Firewall | 🛡️ Yes (Proxy & Rule-based DLP) | ❌ No |
| Audit Traces & Logs | 📝 Yes (Prompt recording & compliance) | ❌ No |
| Local LLM Prompt Sanitization | 🦙 Yes (Ollama integration) | ❌ No |
| Persistent Agent Memory | 🧠 Yes (survives restarts & sessions) | ❌ No |
| Agentic Web Search | 🌐 Self-hosted SearXNG | ❌ Usually No |
| Capabilities | 🛠️ 27+ specialized tools | ⛏️ 1 to 5 basic tools |
| Configuration | 🖥️ Web GUI Dashboard OR ⚙️ Manual | ⚙️ Manual JSON setup |
| Privacy | 🔒 100% Local Execution | 🔒 Varies |
- 🛡️ LLM Prompt Firewall: Intercept, sanitize, and perform prompt recording for all data leaving your system, ensuring robust AI security.
- 🔒 100% Privacy-First: Everything runs locally. Generate reliable audit traces for AI usage while your code and data never leave your machine unaudited.
- 💸 Truly Free: No accounts, no paywalls, no subscriptions.
- 🧠 Persistent Agent Memory: Let your AI remember facts and contexts across sessions seamlessly.
- ⚡ Plug & Play: Installs instantly via
uvxorpip. MCP configuration supports both manual JSON and GUI workflows.
📋 Table o
Tools (3)
web_searchPerforms web searches using self-hosted SearXNG.prompt_sanitizeSanitizes prompts by removing PII and secrets using local models.memory_storeStores and retrieves persistent agent memory across sessions.Environment Variables
OLLAMA_BASE_URLURL for local Ollama instance used for prompt sanitization.Configuration
{"mcpServers": {"agentic-store": {"command": "uvx", "args": ["agentic-store-mcp"]}}}