owasp-agentic-mcp 1.0.4

OWASP Top 10 for AI Agents security assessment tools. Capabilities: full agent security scan, prompt injection detection, tool poisoning check, excessive agency, data leakage. Built by MEOK AI Labs.

OWASP Agentic AI MCP

Security assessment against the OWASP Top 10 for Agentic AI (2025). Prompt injection detection, tool poisoning checks, excessive agency evaluation, and data leakage analysis.

Install · Tools · Pricing · Attestation API

---

Why This Exists

The OWASP Top 10 for Agentic AI (released 2025) defines the ten most critical security risks for AI agents that can take actions, use tools, and operate autonomously. As organisations deploy MCP servers, LangChain agents, and autonomous AI workflows, these systems face attack vectors that traditional AppSec testing does not cover.

Prompt injection, tool poisoning, excessive agency, and cross-context data leakage are not theoretical: they are actively exploited. CISOs and security teams need a structured way to assess agentic AI deployments against the OWASP classification. This MCP evaluates your agent architecture against all 10 risk categories and produces actionable findings.

Install

pip install owasp-agentic-mcp

Tools

Tool	OWASP Reference	What it does
assess_agent_security	All 10 risks	Full security posture assessment against OWASP Top 10 for Agentic AI
check_prompt_injection	Risk A01	Detect prompt injection attack vectors in agent inputs
check_tool_poisoning	Risk A02	Evaluate tool definitions and MCP configs for poisoning risks
check_excessive_agency	Risk A03	Assess whether agent has more permissions than needed
check_data_leakage	Risk A06	Identify cross-context data leakage paths in agent workflows

Example

Prompt: "Assess the security of our customer support AI agent.
It has access to 12 MCP tools including database queries, email
sending, and file system access. It operates on user prompts
with no input sanitisation."

Result: Assessment across all 10 OWASP Agentic AI risks with critical
findings: A01 prompt injection (no input sanitisation on user prompts),
A02 tool poisoning (3 MCP tools loaded without integrity checks),
A03 excessive agency (file system + email + database = over-privileged),
A06 data leakage (database query results passed through to email tool
without redaction). Remediation priorities and control recommendations
provided for each finding.

Pricing

Tier	Price	What you get
Free	£0	10 calls/day — agent security assessment
Pro	£199/mo	Unlimited + HMAC-signed attestations + verify URLs
Enterprise	£1,499/mo	Multi-tenant + co-branded reports + webhooks

Subscribe to Pro · Enterprise

Attestation API

Every Pro/Enterprise audit produces a cryptographically signed certificate:

POST https://meok-attestation-api.vercel.app/sign
GET  https://meok-attestation-api.vercel.app/verify/{cert_id}

Zero-dep verifier: pip install meok-attestation-verify

Links

• Website: meok.ai
• All MCP servers: meok.ai/labs/mcp/servers
• Enterprise support: [e-mail]

License

MIT