Security

MCP server for Steampunk Spotter: Lets AI agents verify Ansible and Terraform code against your policies.

Sorb task tools for external MCP agents

Run scoped, authorized Sn1per pentest, recon and attack surface scans from AI agents; read findings.

Information-flow control for AI agents: a zero-dependency MCP proxy that stops prompt-injection-driven data exfiltration.

Local stdio MCP connector for Pullini artifacts (E6, T6).

Authorization-gated penetration testing MCP server for agentic AI

A secure, read-only MCP interface for OSIRIS research information systems.

MCP server exposing opencpt CPT (cone penetration test) analysis tools to LLM clients

Nexargio Abhedya Sovereign AI Defense Suite for MCP (Multi-Modal Scanner, AI-CDR & State Sentinel)

Android dynamic analysis MCP server: adb, Frida, mitmproxy, apktool, jadx

MCP server for the Mixcloud API: search, browse, upload and edit shows

A local MCP server that starts and watches Mindcraft research runs.

Local runtime security scanner for MCP servers — known-CVE checks, one-click fixes

Dynamic red-team harness for MCP agents: a transparent proxy that injects attacks, measures attack success rate, and ships an information-flow mitigation layer.

Security posture scanner for remote MCP servers: OAuth, transport and tool surface, with spec-cited findings and SARIF.

Hardening and trajectory evals for MCP servers that let agents act on booking systems: scoped, audience-bound tokens, OAuth JWTs, an encrypted audit log, encryption at rest, rate limits and a CI eval gate.

OAuth 2.1 browser login for FastMCP servers whose login is a form checked by the service behind them

Runtime probe for MCP cross-tenant response leaking via JSON-RPC id collision (CVE-2026-111770)

Authplane JWT validation adapter for the official MCP Python SDK

A Python SDK for MCP tool integration with LLM providers