Owasp Agentic Mcp
This server brings OWASP's Top 10 for Agentic AI security checks into your MCP workflow. It scans for prompt injection attempts, tool poisoning vulnerabilities, excessive agency issues, and data leakage risks in your AI agent interactions. Built by MEOK AI Labs with EU AI Act compliance hooks baked in, including risk management tracking and bias detection tooling. The core offering is free and MIT licensed, though they pitch enterprise tiers for SLA guarantees and custom development. You'd reach for this when you need to audit agent behavior against OWASP security standards or when regulatory compliance documentation matters for your deployment.
- tools
- 5
- transport
- STDIO
- last updated
- Aug 19, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
full_agent_scanFull OWASP Agentic Top 10 security scan
Full OWASP Agentic Top 10 security scan
No parameter schema in public metadata yet.
assess_agentic_securityAssess against specific OWASP Agentic categories
Assess against specific OWASP Agentic categories
No parameter schema in public metadata yet.
check_prompt_injectionTest for prompt injection vulnerabilities
Test for prompt injection vulnerabilities
No parameter schema in public metadata yet.
check_tool_poisoningCheck for tool poisoning risks
Check for tool poisoning risks
No parameter schema in public metadata yet.
check_excessive_agencyAssess agency level vs minimum required
Assess agency level vs minimum required
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Owasp Agentic MCP
OWASP Top 10 for Agentic AI security MCP server — prompt injection detection, tool poisoning, exc...
OWASP Top 10 for Agentic AI security MCP server — prompt injection detection, tool poisoning, excessive agency, data leakage assessment
OWASP Agentic MCP
OWASP Top 10 for AI Agents Security Assessment — Prompt Injection, Tool Poisoning, Data Leakage
🚀 Quick Start
# Install via pip
pip install owasp_agentic_mcp
Details
- Repository
- github.com/csoai-org/owasp-agentic-mcp
- Categories
- AI & LLM Tools, Security & Pentesting
- Package
owasp-agentic-mcp- Transport
- STDIO
- Registry
- MCP registry, active
More from csoai-org
- Password Ai Mcp
- Patient Safety Ai Mcp
- Pci Dss Mcp
- Pdf Merge Ai Mcp
- Pdf Tools Ai Mcp
- Performance Ai Mcp
- Personal Finance Ai Mcp
- Photography Ai Mcp
- Plagiarism Checker Ai Mcp
- Planthire Ai Mcp
- Price Tracker Ai Mcp
- Project Management Ai Mcp
- Quiz Generator Ai Mcp
- Readme Generator Ai Mcp
- Recipe Finder Ai Mcp
- Recruitment Ai Mcp
- Regex Ai Mcp
- Robotics Control Mcp
- Schema Validator Ai Mcp
- Security Scanner Ai Mcp
- Self Healing Infrastructure Mcp
- Sentiment Analysis Ai Mcp
- Sleep Tracker Ai Mcp
- Supply Chain Mcp
Related AI & LLM Tools MCP servers
View all
Mcp External Memorydaedalus/mcp-external-memoryAn MCP server that gives LLMs persistent, searchable semantic memory0stars
Agent Signaldan24ou-cpu/agent-signalCollective intelligence for AI shopping agents — product intel, deals, and more0stars
Agent Guardrail MCP Servereren-solutions/agent-guardrailAction-level governance for AI agents -- control what they DO, not what they SAY0stars
Ragfieldcure/fieldcure-mcp-ragMCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.0stars
Giskard Memorygiskard09/giskard-memoryPay-per-use semantic memory for AI agents. SHA256 commitment, Ed25519 sig, Lightning.0stars
User Promptjacob-j-thomas/user-context-retrieval-mcp-serverAn MCP server that enables AI agents to ask users clarifying questions via pop-up terminal windows.0stars