- 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.
Openclaw Assistant
Hardened, self-hosted AI assistant on the OpenClaw gateway: Claude over Telegram with least-privilege mail, drive, calendar, GitHub, and web browsing, behind a default-DENY egress…
Pnx MCP Audit
Security audit CLI for Model Context Protocol (MCP) servers. Zero deps, offline, cross-platform.
Bert Bouncer
On-device prompt-injection firewall for Claude Code. Hybrid DeBERTa + masked-LM detection with span localization, content sanitization, and a reproducible red-team evaluation. No…
Axguard
Adversarial security testing for AI agents — MCP, A2A, x402/L402, and live tool-use. Tests as YAML, evidence as JSON.
AI Threats
AI-related threat intelligence pipeline with KEV/EPSS enrichment, MCP server, and Claude-powered classification
Guarded Server
An MCP server with a real security model and the tests that prove it: three permission tiers with human approval for destructive tools, a path jail, tool results marked as untrust…
Kimi Code Security Hook
PreToolUse security gate for Kimi Code: blocks secret exposure & SSRF before WriteFile/Shell via correctover-scan (MCP config security)
Webmcp Sentinel
Server-enforced authorization, human approval, and audit for AI-agent actions — a WebMCP security reference implementation
Two Stage Sanitization Architecture
Two-stage security architecture to mitigate indirect prompt injection attacks in rich content via privilege separation
Skeptic
SKEPTIC — the local text forensics lab. Paste anything, trust nothing, transmit nothing. 9 deterministic instruments · zero dependencies · browser app + REST API + MCP server.
Crewai Agentlock
Per-tool authorization for CrewAI agents. Every tool call gated, logged, and cryptographically signed.
AgentSecGateway
Open-source scanner for AI agent skills, MCP servers, and coding-agent security risks.
Agent Payment Guard
Pre-pay risk gate for autonomous payment agents — block prompt-injected destinations, intent mismatches & overcharges before your agent signs. Claude Agent SDK PreToolUse hook + a…
Damn Vulnerable Agent Asset Corpus
Damn Vulnerable Agent Asset Corpus: benchmark fixtures for agent-asset scanners and AAC release assurance.
Dvarapala
द्वारपाल — gatekeeper between your LLM and third-party MCP servers. Reads every JSON-RPC message, denies what fails policy, redacts what leaks, audits the rest.
Adversa
LLM red-team harness — OWASP LLM Top 10 + MITRE ATLAS attack packs
Hades Blackwatch
Hades Blackwatch is an advanced AI security and code-review skill for auditing LLM, agentic, MCP, and full-stack applications using OWASP LLM/Agentic Top 10, AIVSS, MITRE ATLAS, N…
Groundforge MCP Inspector
GroundForge MCP Inspector is a local-first CLI that inspects MCP servers before agents connect to them. It discovers tools, prompts, resources, schemas, and metadata, then flags r…
Prompt Injection As An Architectural Primitive
Paper, harness, and raw data: why detection fails against semantic poisoning in agentic LLM pipelines.
Logbook Agent
Local-first, tamper-evident audit trail for AI agents. The operator holds the only key; the agent vendor can neither read nor forge the record. Includes a byte-transparent MCP pro…
LLM Engineering Portfolio
Thirteen measured experiments on one RAG pipeline: retrieval evaluation, hallucination defense, prompt injection, MCP, and stateful agents. Every number produced by code in this r…
AI Act Evidence Desk
Agentic RAG assistant that turns an AI use case into a source-grounded EU AI Act evidence map. Hybrid BM25/TF-IDF retrieval with rank fusion, three-pass self-consistency synthesis…
Agentic Redteam Harness
A/B red-team harness for agentic AI: 34 OWASP-LLM / MITRE-ATLAS attacks fired at a multi-agent app with and without a control plane, plus a live malicious-MCP-server demo. Determi…
Tool Poisoning Scanner
Paste an MCP server's tool definitions and statically scan them for prompt injection, hidden characters, tool shadowing, and exfiltration-shaped parameters before you install it.
Whaleguard Redlab
Local-first, scope-guarded AI red-team lab for authorized LLM, Agent and MCP security evaluation.
Py Agentlint
Lint MCP configs, agent permission settings and CLAUDE.md/AGENTS.md offline: unpinned launchers, literal secrets, blanket permissions, prompt injection, hidden Unicode (Python, st…
Hallumark
LLM hallucination & grounding auditor for RAG systems
Prompt Shield Security MCP
Deterministic prompt injection classification, secret entropy detection, PII redacting, and synthetic dataset bias auditing.
AI Security Skill
A prompt-based security audit for AI systems. Copy it, paste it into any AI assistant with codebase access, and get a structured vulnerability report in minutes.
Security Toolkit
13 atomic MCP tools for AppSec and AI Security: recon, MCP audit, prompt-injection audit, OWASP LLM Top 10
Psp Cdl
Public-domain PSP and CDL standards, reference LLM/MCP proxies, and reproducible workflow-security evaluation. Sponsored by RealflowCloud, Inc.
Cutout
Offensive framework for authorized security testing of agentic AI systems — recon, exploit, persist, and pivot across MCP servers and agent chains.
LLM Agent MCP Security Lab
Deliberately vulnerable local lab for hands-on LLM agent & MCP security testing; SSRF, path traversal, SQLi, indirect prompt injection, RAG poisoning, stored XSS and each with a S…
Redteam Lab
A red-team lab for the MCP discovery surface: instructions-field prompt injection, cacheScope:public cross-caller cache poisoning, and post-approval drift, with four controls that…
Lagrange
Byzantine Fault Tolerant consensus middleware that protects AI agent memory from poisoning attacks (MINJA, indirect prompt injection). Every write is validated by three independen…
Divergence
Precision-first security analyzer for MCP servers and agent skills. 0% false positives on traps, 96% recall.
Codelytra
Open-source, local-first AI security scanner for JavaScript and TypeScript LLM, agent, RAG, tool-calling, and MCP applications.
Renker Agent Demo
Runnable demo: renker-core-authz secures an AI agent's tool calls (ALLOW/DENY/REQUIRE_APPROVAL) against prompt injection, via an MCP server + tamper-evident audit log
Osanwe Public
A Markdown vault for financial analysis, run by AI agents, in which research compounds: each analysis is written back as typed, linked notes that the next one reads first. Broker…
Sentricore Agent Security
Security gateway for AI agents on REST and MCP: prompt-injection defense, tool governance, human-in-the-loop escalation, tamper-evident audit logs.
Sentori
🛡️ Security scanner for AI Agents and MCP Servers — like npm audit for AI
Peakstar Mcpguard
MCP / Agent security scanner: scan for security holes before your AI agent touches company systems. Zero dependencies, static, runs locally, sends nothing out.
Proven Gate
Deterministic provenance policy layer between LLM agents and their tools (including MCP) — blocks tool calls driven by untrusted data. No LLM, no network, fail-closed.
State Of MCP Security
Reproducible security audit of MCP servers — 75% of scanned servers exposed a medium+ hardening issue to AI agents. Round 1: official reference + popular hosted servers.
Agentomy Agent
Free-forever governance peer for AI agents. Score, flag, and audit any agent session in 30 seconds, no infrastructure. Open (MIT) system prompt plus TypeScript/Python SDK. Part of…
Toolwall
Information-flow firewall for MCP tool calls: tracks what a session has read and blocks the call that would send it out.
Agent Security Studio
Flagship AI agent security studio with risk simulation, tool approvals, RAG evals, traces, GitHub audits, tests, CI, and Pages deploy.
Aitdp
AI Threat Detection Protocol — open spec, community ruleset and reference SDK for detecting prompt injection, jailbreaks, data exfiltration and tool abuse in LLM apps and AI agent…
Skillrank
What can this agent skill actually do to your machine? Static security grading for AI agent skills — 3,771 scanned in seconds, zero API cost.
Razorpay Hackathon Agentic Gateway
Zero-trust payment gateway for AI agents: Ed25519-signed AP2-style mandates, two-phase reserve/settle on Razorpay, layered prompt-injection guards (regex + Llama Prompt Guard 2),…