Agent Prompt Injection Firewall Mcp

Overview

Agent Prompt Injection Firewall Mcp is a Model Context Protocol (MCP) server: The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume... As an MCP server it plugs straight into AI assistants, exposing its functionality as tools the model can invoke on your behalf.

You can run Agent Prompt Injection Firewall Mcp two ways: connect to the hosted endpoint at https://api.meok.ai/v1/a2a/prompt-injection-firewall with no local install, or run it on your own machine via the Python package agent-prompt-injection-firewall-mcp (via uvx). The current release is v1.0.13, published under the MIT license, with source at CSOAI-ORG/agent-prompt-injection-firewall-mcp on GitHub.

You'll find Agent Prompt Injection Firewall Mcp in the AI & Agents category here on mcp.site; it connects to Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and any other MCP client — see the install snippets below. If you maintain Agent Prompt Injection Firewall Mcp for CSOAI-ORG, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

Settings → Connectors → Add custom connector
Name: Agent Prompt Injection Firewall Mcp
URL:  https://api.meok.ai/v1/a2a/prompt-injection-firewall