- Conduid
- Marketplace
- #prompt-injection
MCP servers tagged prompt-injection
604 live MCP servers tagged "prompt-injection", 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.
Heldfast
You approve an MCP server. Heldfast records what you approved. Later it tells you what moved, and guard refuses the rest.
Verus
Security infrastructure that converts untrusted financial content into verified, signed context for trading agents.
Unmask
Reveal the hidden Unicode an LLM reads: zero-width chars, bidi overrides, invisible tag payloads, and homoglyphs in any prompt or skill file. Client-side.
Agent Risk Linter
Offline-first security linter for Agent Skills, MCP configs, scripts, and CI workflows.
FourEyes
Human-gated support agent: dual MCP servers, LangGraph interrupts checkpointing before every irreversible write, three defense layers red-teamed against prompt injection.
Agent Boundary
A deterministic tool-call broker that bounds what an LLM agent can actually do. Indirect prompt injection is assumed to succeed; authorisation lives outside the model.
Asitis Agent Tools
Read-only MCP server and Claude Code plugin that lints CLAUDE.md, AGENTS.md and SKILL.md, counts approximate tokens per file, flags hidden instructions and invisible characters, a…
Claude Code Self Defense
Claude Code self-defense hooks — security hooks for AI coding agents
VortoCode
Self-hosted AI coding agent: one agent runtime behind Desktop, TUI, Web and headless CLI. Delegated dev tasks run in isolated git worktrees with verification and PR handoff; human…
RogueAgent Testbed
Georgia Tech master's in cybersecurity research on cascading indirect prompt injection attacks. Author: Fahid Ahmed
Sleeper
Local-first agent tool-call assurance lab: injection → tool action → control gate → evidence.
Still Untrusted
From-scratch TypeScript reimplementation of Microsoft Agent Framework's FIDES label algebra, checked against its spec.
Agentic Semgrep Rules
Semgrep rules for AI agent code: static analysis for LLM applications in Python, TypeScript and JavaScript. Finds model output reaching exec, shells, SQL, URLs, files and HTML, us…
Skill Scan Gate
CI gate for Claude Code skills and plugins: scans a skills or plugin repository for instruction-override text, exfiltration patterns, dangerous hook commands, unpinned MCP servers…
Guardian
MCP Guardian acts as a proxy service for remote MCP endpoints, and constantly polls them to make sure they haven't been compromised or modified.
Glyph
🔮 MCP security scanner — find tool poisoning, credential leaks, and insecure transports in AI agent configurations
Guard
Security scanner for MCP (Model Context Protocol) servers: detects tool poisoning, prompt injection, command injection, path traversal and leaked secrets. SARIF, GitHub Action, si…
Www Project Agent Memory Guard
OWASP Foundation web repository
Www Project Agent Memory Guard
OWASP Foundation web repository
Lint
Static security linter for MCP tool definitions — catch prompt injection, tool poisoning & unconstrained schemas before your agent loads them
Firewall
Scan and gate Model Context Protocol servers for tool poisoning, rug-pulls, and indirect prompt injection.
.github
Org profile and community health files for Responsible AI Labs. RAIL Score: LLM evaluation across 8 dimensions, guardrails, MCP server, red-teaming, and India DPDP / EU AI Act com…
LLM Blue Team Guardrail
A layered LLM guardrail (fast heuristics + an LLM judge) against prompt injection, with a guarded RAG pipeline that quarantines poisoned documents and an MCP server for AI agents.…
Audit
Python security scanner for Model Context Protocol (MCP) servers — find prompt injection, over-broad permissions, weak input validation, and credential leaks before your AI agent…
Securing MCP Servers
Notes and exercises for the O'Reilly live course: Securing MCP Servers — exploitation and defense of Model Context Protocol implementations.
AI
Пет-проекты: MCP-серверы и LLM-агенты на .NET 10 — SQL-аналитик с защитой от prompt injection, CRM для AI-агента, навигация по C# для AI-код-ревью
Mcpcheck
Correctness checks for MCP servers — prompt-injection lint, contract drift, over-broad tools, dishonest annotations. Never calls a tool.
Agentgate
The open-source firewall for AI agents.
Red Team
mcp security scanner. mid-2025. deprecated.
Warden
A security proxy for the Model Context Protocol. Every tool call gets integrity-checked, policy-checked, inspected, and audited before it runs.
Preflight
Capability-aware risk scoring for AI coding agent tool calls. Five-dimensional decomposition, session-graph composition, repo awareness, the Agent Control Plane and Confused Deput…
SkillScanner
Universal AI agent skill security scanner. 5-layer deep defense for prompt injection, MCP tool poisoning, encoding obfuscation. Zero dependencies. Bilingual EN/ZH.
Agent Cordon
Zero-dependency prompt-injection and data-exfiltration firewall for LLM agents: scans untrusted text and outbound actions, sees through obfuscation, guards the MCP/tool boundary.
Cybersec MCP
Security-tooling MCP server with SSRF guards, prompt-injection containment and a hash-chained audit log
Ares
Offensive security framework for autonomous AI agents — recon, foothold, provenance desync, coherence-evasion pacing, recovery poisoning, and exfil, gated by signed attestations a…
Canary
Which fields of an MCP tool result actually reach the model's context, measured with benign canaries across every installed server
Safe Skills
🛡️ Zero-trust security gate & vulnerability scanner for AI agent skills (Claude Code, Antigravity, OpenCode, Codex). Powered by NVIDIA SkillSpector.
NL Automation Platform
Create useful automations just by describing what you want in plain English — no scripts, complicated setup, or guesswork.
Qec Demo Agents
Seven platform scenarios (AWS, Google, Anthropic, IBM, Salesforce, ServiceNow, SAP), each exploited then governed; every ledger verifiable.
Agent Vault
A local credential proxy for coding agents: the agent sends a placeholder and never holds the secret. Free and open source from ioLite Labs.
Heatlot
Every certificate, checked against the record. AI verification of supplier CoCs and mill test reports at receiving inspection: the AI extracts, rules decide, every field cited, si…
Trust Me Bro
Every skill you install says trust me bro. This one reads it first. Pre-install audit for agent skills, plugins, and MCP servers: lethal-trifecta reach, injection wording, provena…
Mayi
Argument-level authority for AI agent tool calls. Every argument has one owner (app, model, human or derived). Plain deterministic rules, no judging model. Held calls wait for a p…
Security Auditor
Security auditor for MCP servers. Detects tool poisoning, risky tools and leaked secrets using rule checks and an LLM, with verified evidence for every finding.
Portcullis
A firewall and flight recorder for AI tool calls. Proxies MCP traffic, records every call, and enforces policy.
Awesome MCP Security
Curated, auto-updating list of tools, standards, and research for securing Model Context Protocol (MCP) servers.
Gateway
Production security gateway for Model Context Protocol — auth, RBAC, rate limiting, prompt injection detection, and audit logging for MCP servers.
Mcpguard
CLI security scanner for MCP (Model Context Protocol) packages — detects hardcoded secrets, prompt injection, supply-chain attacks, and missing auth in npm-based MCP servers
Gateway
Open-source security gateway for MCP — block SSRF, secret leaks, prompt injection, and cross-tool exfiltration
Check
Offline MCP security scanner for Model Context Protocol configs and SKILL.md bundles