MCP servers tagged prompt-injection-defense

9 live MCP servers tagged "prompt-injection-defense", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with prompt-injection-defense.

live servers

avg trust

Tuxnews

An agent-native, AI-powered news engine that learns your taste, eliminates clickbait, archives local Markdown, and serves LLM agents via FastMCP.

Aegis SSH MCP

MCP-native SSH bridge for AI agents with host-scoped access, rule-based command validation, ephemeral SSH sessions, and audit logging

Zn

Zero-trust, bidirectional prompt injection & tool-poisoning security gate for AI agents.

Verdict Studio

Visual multi-agent debate pipeline builder, live token streaming playground, and scoped Model Context Protocol (MCP) tool security gateway for Haize Labs Verdict.

Job Radar

Secure read-only MCP server for typed job search, deterministic ranking, explainable matching, adversarial defenses, and audited tool use.

Belay

Belay is an open-source, local-first security layer for AI coding agents (Claude Code, Codex, Cursor, OpenClaw, Hermes Agent and MCP) that blocks dangerous commands, secret leaks,…

Security Patterns

MCP security patterns — 10 production implementations mapped to OWASP MCP Top 10. Prompt injection, credential isolation, HITL governance, session recording. Working attack demos…

AgentInterdict

AgentInterdict — runtime enforcement for autonomous AI agents. Trust context. Verify authority. Interdict unsafe action.

Auto Fill Forms

Human-in-the-loop job-application autofill agent: Claude Code + Playwright MCP fill forms from your profile; you always click Submit.