Scanning MCP Servers with ZAP

On May 21, 2026, the ZAP project announced a new MCP Integration add‑on that enables the OWASP Zed Attack Proxy (ZAP) to scan Model Context Protocol (MCP) servers. MCP servers expose tools, resources, and prompts to AI assistants over JSON‑RPC; they are treated as a new kind of API. The add‑on imports an MCP server’s endpoints into ZAP by performing the MCP handshake, enumerating all exposed tools/resources/prompts, and sending representative requests (with string arguments populated by ZAP’s value generator) to capture JSON‑RPC requests/responses in the history and sites tree. Once imported, all existing ZAP capabilities apply: passive scanning, active scanning, fuzzing, and reporting. The add‑on is available from the ZAP desktop Marketplace, from the Automation Framework via a new `mcp-import` job, and from GitHub Actions using the `zaproxy/action-mcp-scan` action. The post warns that active scans send mutating `tools/call` requests, so they should be run against test deployments. MCP‑specific scan rules (e.g., prompt‑injection via tool descriptions, dangerous tool capabilities) are not yet implemented but are planned for future releases. Feedback is requested via the ZAP User Group or GitHub issues.

https://www.zaproxy.org/blog/2026-05-21-scanning-mcp-servers-with-zap/

Comments

Post a Comment

Popular posts from this blog

Prompt Engineering Demands Rigorous Evaluation

In the blog post “Prompt Engineering Requires Evaluation” on the Shostack + Associates website, the author argues that treating prompts for large language models (LLMs) merely as creative artefacts is insufficient. Engineering prompts properly demands structured evaluation frameworks — what the AI community calls “evals” — to test which prompt versions work better, with which models, and under which conditions. The post highlights that simply assuming a prompt is “good enough” creates risks when LLMs are integrated into production systems (e.g., for threat modeling). It advocates for measuring prompt performance, variation effects, and tool-chain dependencies (model, context, ancillary materials).  Ultimately the message is: prompt engineering should borrow disciplined practices from software engineering (versioning, testing, benchmarking) rather than relying on informal experimentation.  https://shostack.org/blog/prompt-enignieering-requires-evaluation/
Read more

SecObserve: Simplified Vulnerability and License Management for CI/CD Pipelines

 SecObserve is an open-source tool for managing vulnerabilities and licenses in software development and cloud environments. It integrates various vulnerability scanners into CI/CD pipelines using GitLab CI templates and GitHub Actions for streamlined setup. It offers a centralized dashboard for assessing and reporting vulnerabilities, with tools for filtering, sorting, and evaluating results. SecObserve supports automation and manual assessments to focus on resolving critical issues.  https://github.com/MaibornWolff/SecObserve/tree/dev
Read more

Top Post-Quantum Cryptography Solutions and Vendors Ranked for Quantum-Safe Security

The article reviews and ranks nine post-quantum cryptography providers whose products use NIST-approved quantum-resistant algorithms to safeguard systems as quantum computing advances, driven by impending federal mandates and increasing enterprise demand. It evaluates vendors on security strength, performance, ease of integration, deployment history, use-case support, and roadmap, highlighting offerings spanning blockchain protection, enterprise crypto-agility, hardware-level security, PKI lifecycle tools, quantum entropy key systems, and quantum key distribution to address the transition from classical cryptography to quantum-safe defenses.  https://aijourn.com/top-9-post-quantum-cryptography-solutions-compared-pqc-providers-ranked/
Read more