- 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.
AegisForge MCP
Zero-trust AI security research engine built on MCP, Tauri v2, and Rust — with prompt injection defense and sandboxed tool execution
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…
Jakk
Black-box security scanner for MCP servers — deterministic single-call probes, no LLM. 13 probes across 7 surfaces.
Mcpkernel
The Security Kernel for AI Agents — MCP/A2A gateway with policy enforcement, taint tracking, sandboxed execution, deterministic envelopes, and Sigstore audit. OWASP ASI 2026 compl…
Scan Action
The first GitHub Action that scans MCP servers, AI agents & LLM pipelines for security vulnerabilities. 24 checks: tool poisoning, SSRF, prompt injection, DataFlow taint. Results…
Attestral
Open-source security scanner for MCP servers and AI agents: finds prompt injection, tool poisoning, and excessive agency, and models the cloud your agents can reach. pip install a…
Synapsor Runner
Let AI agents query and update Postgres/MySQL without raw SQL, unrestricted schema access, or database credentials in the model; writes stay reviewed.
Autoagent
Zero-dependency LLM agent runtime — tool use, MCP, sandboxed self-written tools, checkpoint/resume, approval gates, bi-temporal fact memory, code-level guards (context bounds, loo…
Aletheia Paper
Aletheia: A Taxonomy and Empirical Evaluation of Behavioral Failure Patterns in Large Language Models
AI Tooling
MCP servers for red-team tooling (Mythic C2, BloodHound, nmap) plus LLM red-team reference: prompt injection / secret extraction and insecure output handling (XSS), each with a pr…
Safe MCP Agent
A local LLM agent (LangGraph + MCP) with a red-teamed guardrail layer and an automated evaluation harness that benchmarks security and task performance across models.
Eslint Plugin Security MCP
ESLint rules to detect prompt-injection vectors in Model Context Protocol server code
Agent Security Kit
Practical audit tools and controls for securing MCP servers and agentic AI tool access.
Pyrit MCP Server
Arm any MCP-capable agent to autonomously red-team a target LLM. Microsoft PyRIT exposed as 31 composable MCP tools: attacks, scoring, converters & scenarios
PAL MEM
Context filter + AI SBOM + retrieval engine for agents working against corpora larger than any model's context window. Local-first, markdown-native, MCP-ready. Haiku 4.5 reac…
AnB MCP
MCP server front-end for AnB — let AI agents use secrets without ever seeing the plaintext. Go + official MCP go-sdk; security logic delegated to alice (redaction, exec allowlist,…
Palisade
A firewall for AI agents — policy, egress control, prompt-injection quarantine, and a tamper-evident audit log for any MCP server
Hachiman Agent
Hachiman Agent — autonomous security layer for AI agents and MCP. Scan before deployment, authorize before access, monitor during execution, contain when compromised, report every…
Memwall
Antivirus for AI agent memory - scanner + MCP firewall for memory poisoning (OWASP ASI06)
Defense Bench
Vendor-neutral benchmark measuring how MCP security proxies/gateways DEFEND against 22+ attack vectors — crosswalked to NIST AI RMF & OWASP LLM/Agentic Top 10. CI-gated, reproduci…
Injection Lint
Semantic prompt-injection & tool-poisoning linter for MCP servers. Precision-first, 100% local — tells real injection apart from legitimate tool descriptions.
Ephorate AI Governance And Monitoring
Open-source control plane for AI agent security & governance — runtime policy enforcement, tamper-evident audit, prompt-injection detection (SIEM/EDR) and compliance mapping (NIST…
Be My Geminis
Routes every image Claude Code touches through Gemini Vision into typed JSON. Video, MCP, structured visual diff, and a quiet Opus fallback when Gemini's down.
Agentmoat
A security layer for AI agents: detects prompt injection, firewalls dangerous tool calls, scores inter-agent trust, and keeps a tamper-evident audit log. Works with the Anthropic…
Cross Provider Egress Guard
Destination-aware, default-deny egress control for AI coding agents, at the tool-dispatch layer across Claude Code and Codex from one shared policy.
Bedrock Security MCP
ARCHIVED: development moved to github.com/AUAggy/agent-sec-scanners (packages/bedrock). npm package unchanged. MCP server + CLI auditing AWS Bedrock security posture: IAM, logging…
Cupel
Assay every skill, plugin, and MCP server your coding agent loads. One local command grades safety, token cost, and quality.
Exploit Validator
Proves whether AI agent (MCP) tool configurations are actually exploitable - not just risky-looking. Existing scanners infer risk from manifests; this one validates it in a sealed…
Loomdb
An agent-native database. Sessions are branches an agent can fork, merge, and rewind; every write records what it was derived from; and taint-and-recall tells you exactly what a p…
Codex MCP Doctor
'npm doctor' for MCP. Diagnose broken servers, Cyrillic homoglyph attacks, and silent rug-pulls - zero deps, 287 tests. Built in Codex with GPT-5.6.
Safemcp Gateway
MCP security gateway with zero dependencies - blocks prompt injection, path traversal and SSRF attacks on AI agents.
Pcap MCP
Secure MCP server for AI-assisted PCAP analysis with tshark, redaction and prompt-injection defense.
Openfloor
A WebMCP-native live auction house where AI agents bid inside human-set mandates they structurally cannot exceed. Your agent bids. You set the limits. Everything on the record.
Trust Issues
Adversarial security review for AI skills, repos, MCP servers, and packages before you install them. A read-only scanner plus a five-persona reasoning pass, ending in a GO / GO WI…
AISecuritySecondBrain
AI/LLM security knowledge base — OWASP LLM Top 10, MITRE ATLAS, prompt injection, agentic security. An Obsidian vault: 92 interlinked, fully-cited pages.
Malskanner
Scan a repo for hidden prompt-injection before your AI agent trusts it — CLI, MCP server & GitHub Action. Run: npx malskanner <repo>. 0 false positives across 5,620 files.
Prompt Injection Defense
The language-level attack defense skill every agent should keep. Covers 12 attack categories. Works with Claude, GPT, Gemini, Copilot, and any LLM.
AgentInterdict
AgentInterdict — runtime enforcement for autonomous AI agents. Trust context. Verify authority. Interdict unsafe action.
AI Security Red Team Testing Guide 2026
AI Security: Red Team Testing Guide 2026
Polaxis SDK MCP
Python SDK and MCP server for Polaxis - AI agent governance platform. Evaluate every tool call against policies in real time: block dangerous actions, enforce budgets, route to hu…
AI Security
Open-source, self-hosted Fastest AI security gateway for LLM and agent apps: guardrails, agentic PDP, semantic caching, MCP gateway.
Inkie Auto Mode
Don't let your agent delete the database. Hybrid static + LLM permission classifier for Claude Code, OpenClaw and Cursor.
CyberAI
AI-powered pentest platform
Verification Security
Public verification, security review, and skill quality process for Agent Skill Exchange
Hacking The LLM AI Goat Red Team
Red teaming AI Goat™ to explore OWASP Top 10 for LLM Applications (2025), prompt injection, RAG poisoning, MCP-assisted auditing, and AI security vulnerabilities.
Rulesentry
Catches hidden and invisible-unicode instructions smuggled into AI coding-agent config and skill files. Zero-config CI check.
Agent Rules Audit
Offline scanner for AI agent instruction files (AGENTS.md, CLAUDE.md, .cursorrules, skills, MCP configs) — flags prompt-injection payloads, hidden Unicode, encoded blobs, exfiltra…
Wardrail
Local security scanner for vibe-coded apps: stop API key leaks, Git-history secrets, and unsafe MCP or AI agent instructions before commit.
Cloudguard
Reliability and safety harness for LLM cloud agents. Tool-selection accuracy vs. tool count, blast-radius guardrails, and prompt-injection red-teaming against a real AWS mock. Eve…
Sinon
AI agent pentest kit: a methodology and 54-probe corpus for prompt injection, tool abuse and over-permissioned agent actions. Verdicts rest on observed facts, not a judge model.