Security & Testing MCP Servers

MCP servers for security scanning, vulnerability testing, secrets management and QA automation. Each entry is scanned with the deterministic Capability-Flow Trust Model — grades are computed, never self-reported.

Idb PyPI
A
idb-mcp

An MCP server and importable Python module that wraps Facebook IDB to control iOS simulators for automation. Implemented by AskUI.

Security & Testing Score 93/100 1 finding Cap. High
Kontrol Freek PyPI
A
kontrol-freek-mcp

AI assumption firewall for MCP agents — intercepts risky decisions, detects contradictions, and gates human approval via Telegram or Slack.

Security & Testing Score 93/100 1 finding Cap. High
Kubectl PyPI
A
kubectl-mcp-server

A Model Context Protocol (MCP) server for Kubernetes with 270+ tools, 8 resources, and 8 prompts

Security & Testing Score 93/100 12 findings Cap. High
Log Essence PyPI
A
log-essence

Intelligent log analysis for LLMs - extract patterns, redact secrets, compress 50%+

Security & Testing Score 93/100 5 findings Cap. High
Memory Shell PyPI
A
memory-shell-mcp

Java内存马检测和清理工具的MCP服务器 - Memory Shell Detector MCP Server

Security & Testing Score 93/100 6 findings Cap. High
Mk Spec Master PyPI
A
mk-spec-master

MCP server bridging specs (Linear / JIRA / GitHub Issues / Notion / Markdown / Figma) to tests, with bidirectional traceability and a spec-quality coach (AI 規格大師)

Security & Testing Score 93/100 1 finding Cap. High
Okta Auth Cli PyPI
A
okta-auth-cli

Okta login toolkit with an interactive CLI and MCP session reuse

Security & Testing Score 93/100 2 findings Cap. High
Openclaw Skill Vetter PyPI
A
openclaw-skill-vetter-mcp

MCP server for security-vetting third-party AI agent extensions before installation — Claude skills, ClawHub plugins, agent tool packs. v1.1: agent-config trust-boundary scanner (AGENTS.md / .cursor/rules.md / .claude/CLAUDE.md / .gemini/config / git hooks) addressing CVE-2026-26268. Outputs 0-100 risk score + BLOCK/REVIEW/CAUTION/CLEAN buckets.

Security & Testing Score 93/100 15 findings Cap. High
Paperqa PyPI
A
paperqa-mcp-server

MCP server exposing PaperQA2 for deep synthesis across scientific papers

Security & Testing Score 93/100 1 finding Cap. Minimal
Pyobfus PyPI
A
pyobfus-mcp

Model Context Protocol server for pyobfus — the Python obfuscator. Lets Claude Desktop, Claude Code, Cursor, Windsurf, and Zed call pyobfus tools (preflight risk check, zero-config init, reverse stack-trace mapping) directly from an agent conversation. PyArmor alternative with first-class AI-debug story.

Security & Testing Score 93/100 2 findings Cap. High
Python Exec Sandbox PyPI
A
mcp-python-exec-sandbox

MCP server for secure Python script execution with automatic dependency management

Security & Testing Score 93/100 8 findings Cap. High
Remote Ssh PyPI
A
mcp-remote-ssh

MCP server for remote SSH operations -- persistent sessions, structured command execution, SFTP file transfer, and port forwarding for AI agents.

Security & Testing Score 93/100 11 findings Cap. High
Renforge PyPI
A
renforge

MCP server, CLI, and web dashboard for Ren'Py visual-novel development

Security & Testing Score 93/100 2 findings Cap. High
Rug Munch PyPI
A
rug-munch-mcp

MCP server for Rug Munch Intelligence — 19 tools for crypto token risk analysis, rug pull detection, and AI forensics

Security & Testing Score 93/100 2 findings Cap. High
Sallyport PyPI
A
sallyport

MCP server bridging Claude Code to a browser extension over WS+HMAC

Security & Testing Score 93/100 3 findings Cap. High
Security Toolkit PyPI
A
mcp-security-toolkit

Atomic MCP tools for AppSec and AI Security engineers

Security & Testing Score 93/100 7 findings Cap. High
Sharepoint Cert PyPI
A
mcp-sharepoint-cert

MCP Server to integrate with SharePoint

Security & Testing Score 93/100 1 finding Cap. High
Sops PyPI
A
sops-mcp

MCP server for creating and managing SOPS-encrypted secrets

Security & Testing Score 93/100 5 findings Cap. High
Ssh Licco PyPI
A
ssh-licco

SSH Model Context Protocol Server - Enable SSH functionality for AI models

Security & Testing Score 93/100 6 findings Cap. High
Superego PyPI
A
superego-mcp

Intelligent tool-call review system for AI agents

Security & Testing Score 93/100 6 findings Cap. High
Unblu PyPI
A
unblu-mcp

A model context protocol server for interacting with Unblu deployments.

Security & Testing Score 93/100 1 finding Cap. High
Linux X64 Official npm
A
@azure/mcp-linux-x64

Azure MCP Server - Model Context Protocol implementation for Azure, for linux on x64

Security & Testing Score 92/100 0 findings 59k/wk Cap. Minimal
Canary Lab npm
A
canary-lab

The independent local harness for AI-repaired Playwright tests — it runs the tests itself, so a green run can't be faked.

Security & Testing Score 92/100 14 findings 665/wk Cap. High
Interactive Brokers Source verified npm
A
interactive-brokers-mcp

MCP server for Interactive Brokers API integration

Security & Testing Score 92/100 0 findings 518/wk Cap. Minimal