
Agent Prompt Injection Firewall Mcp
io.github.CSOAI-ORGPublished by GitHub account CSOAI-ORGv1.0.13Updated Nov 4, 2026
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Overview
A prompt-injection firewall MCP server that scans prompts, RAG documents and tool arguments for injection patterns before an agent acts on them.
- What you can do
- Scan prompts and RAG documents for injection patterns and heuristics
- Check tool arguments before an agent executes a call
- Act as a runtime guard aligned with the OWASP LLM Top 10 first risk
- Run either as a remote endpoint or as a local Python package
- When to use it
- Worth adding when an assistant handles untrusted text, retrieved documents or tool inputs and you want a pre-check layer that flags likely prompt-injection attempts before they reach the model or a tool call.
- Requirements
- Either the remote endpoint at api.meok.ai or a local Python install of the agent_prompt_injection_firewall_mcp package; no authentication, environment variables or headers are declared.
Installation
In SourceWeft
- Open Agent Prompt Injection Firewall Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.CSOAI-ORG%2Fagent-prompt-injection-firewall-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"agent-prompt-injection-firewall": {
"type": "http",
"url": "https://api.meok.ai/v1/a2a/prompt-injection-firewall"
}
}
}README
Agent Prompt Injection Firewall MCP
[MEOK AI Labs] [GSPC] [License] [PyPI]
AI agent prompt injection firewall MCP
AI agent prompt injection firewall MCP. OWASP LLM Top 10 #1 runtime guard. MIT
🚀 Quick Start
✨ Features
- MCP protocol compliant
- Easy installation
- Well-documented API
- Production-ready
- Active maintenance
📖 Documentation
🛡️ Compliance
This MCP server is built with EU AI Act compliance built-in:
- ✅ Article 9 — Risk Management System
- ✅ Article 13 — Transparency & Instructions for Use
- ✅ Article 15 — Bias Detection & Testing
- ✅ Article 26 — FRIA Support (where applicable)
- ✅ Article 50 — AI Content Watermarking (where applicable)
Need help getting compliant? Book a free 15-min diagnostic →
🏢 Enterprise
Need custom development, SLA guarantees, or white-label deployment?
- Pro: $99/mo — Full MCP suite + EU AI Act tracking
- Enterprise: $499/mo — Custom dev + SLA + Dedicated support
View Pricing → | Contact Sales →
🤝 Part of the MEOK Ecosystem
This server is part of the MEOK AI Labs ecosystem — 300+ MCP servers for sovereign AI governance.
📜 License
MIT © CSOAI-ORG
Built with 💜 by MEOK AI Labs · UK Companies House 16939677
Source: README.md at commit 10bb88f
Tools
0Version history
1- v1.0.13LatestSep 16, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listedRequired15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts