Search

Mistral AI testing helpers for MCP Test Harness

Admission control for HTTP MCP servers: only AER-attested agents reach your tools; rogue agents get a JSON-RPC deny.

Microsoft AutoGen agents testing helpers for MCP Test Harness

Forensic audit of mcp-remote: seven OAuth trust-boundary advisories, five CVE records (CVE-2026-51994/51995/51996/51997/52001). Server-selected request path (CWE-918) run against loopback canaries in 62 stable releases, 0.1.32 to the current 0.15.1; selected code and namespace signatures under 12 other npm names; search blind spots above 350 KiB.

Read-only MCP server exposing the dsh-plugin-certification registry: certification grades, snapshots and five-dimension evidence for DeepSeek Harness plugins.

Deterministic software attestation for AI-augmented development — witness, probe, and seal any repo with SHA-256. Fleet registry across 131 VERITAS nodes. Agent-native, zero cloud.

This pattern describes how to implement a Model Context Protocol (MCP) server that integrates three industry-standard security scanning tools (Checkov, Semgrep, and Bandit) to provide comprehensive code security analysis. The server enables AI coding assistants like Kiro and Amazon Q Developer to automatically scan code snippets.

Enables users to retrieve Hong Kong government security incident reports from the Digital Policy Office. Provides a FastMCP interface for querying the number of reported information security incidents.

Model Context Protocol (MCP) implementation for interacting with Impart's API

enterprise grade mcp security

MCP server with security tools

Bridge AI assistants to 50+ Kali Linux security tools. Solve CTF challenges, perform penetration testing, and automate offensive security workflows across Pwnable, Crypto, Forensics, Cloud, and Web3.

Universal authentication & security engineering engine for Cursor, Claude & Windsurf. Generates production OAuth2/OIDC flows with PKCE, audits JWT tokens for cryptographic vulnerabilities, builds multi-tenant RBAC matrices, and provisions secure API key architectures. NEW v1.1 - audit_password_strength: Audits any password with REAL local math: charset entropy in bits, pattern detection and crack-time estimates at 3 attacker speeds - never stored or transmitted.

Active security scanner for A2A and MCP servers

Secure fetch to prevent access to local resources

Formally-verified injection/exfiltration detector for AI agents (MCP-02).

Context intelligence for AI coding agents: navigation, impact, memory, guarded edits.

NearForm Accelerator for Cloud Native Serverless AWS

Private trust registry for MCP tools — approve once, pin cryptographically (박제), detect rug-pulls forever. Self-hosted, AGPL.

Mobile runtime detection workbench for AI (iOS and Android)