Back to Browse
Free
Server data from the Official MCP Registry
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
About
The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Security Report
3.2
Use Caution3.2High RiskThis prompt injection firewall MCP has solid security intent and appropriate permissions for its purpose, but contains several implementation concerns. The server performs unvalidated regex compilation on user-supplied patterns (define_custom_rule), lacks comprehensive input validation on critical functions, and relies on an external attestation API with weak error handling. The fallback auth mechanism exposes the MEOK_API_KEY in logs and comparisons. While the pattern library is well-researched and the core scanning logic is sound, these issues warrant remediation before production use. Supply chain analysis found 3 known vulnerabilities in dependencies (0 critical, 3 high severity). Package verification found 1 issue (1 critical, 0 high severity).
4 files analyzed · 15 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
Unverified package source
We couldn't verify that the installable package matches the reviewed source code. Proceed with caution.
How to Install
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-csoai-org-agent-prompt-injection-firewall-mcp": {
"args": [
"agent-prompt-injection-firewall-mcp"
],
"command": "uvx"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
Agent Prompt Injection Firewall MCP
WAF for AI agents — block prompt injection before it reaches the LLM
Agents that blindly forward user input + retrieved documents to other agents are the #1 production AI vulnerability (OWASP LLM01). This MCP is the pre-flight gate.
By MEOK AI Labs.
Quick Install
| Client | Install |
|---|---|
| Claude Desktop |  |
| Cursor |  |
| VS Code |  |
| Windsurf |  |
| Docker | docker run -p 8000:8000 agent-prompt-injection-firewall-mcp |
| pip | pip install agent-prompt-injection-firewall-mcp |
Install
pip install agent-prompt-injection-firewall-mcp
Tools
scan_promptdefine_custom_rulelist_rulesscan_logsign_firewall_attestation
Claude Desktop
{
"mcpServers": {
"agentpromptinjectionfirewall": { "command": "agent-prompt-injection-firewall-mcp" }
}
}
Tiers
- Free — generous daily limit (100-1,000 depending on operation)
- Pro £199/mo — unlimited + signed HMAC attestations with public verify URLs — subscribe
- Enterprise £1,499/mo — multi-tenant + custom predicate DSL + SIEM webhook push — subscribe
Why this exists
The EU AI Act (Aug 2026), DORA (live), ISO 42001, and OWASP LLM01 Top-10 all demand runtime controls for agent systems — not just deployment-time audits. This MCP is that runtime control layer, emitting cryptographically signed evidence your auditor accepts.
Related MEOK A2A MCPs
agent-policy-enforcement-mcp— per-pair IAMagent-handoff-certified-mcp— signed delegation chainagent-prompt-injection-firewall-mcp— prompt injection WAFagent-rate-limiter-mcp— fleet-wide quotaagent-audit-logger-mcp— hash-chained signed loga2a-governance-bridge-mcp— map A2A to compliance frameworksmeok-attestation-verify— independent cert verifier
License
MIT — MEOK AI Labs, 2026.
Reviews
No reviews yet
Be the first to review this server!
More Security MCP Servers
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
137
Stars
457
Installs
8.0
Security
4.8
Local
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
-
Stars
60
Installs
10.0
Security
5.0
Local
MarkItDown
Freeby Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
120.0K
Stars
18
Installs
6.0
Security
5.0
Local