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.

Dns Security npm
A
dns-security-mcp

DNS security intelligence MCP server — 104 tools for DNSSEC validation, hijacking detection, tunneling analysis, typosquatting, email security, certificate transparency, blocklist checking, infrastructure audit. 100% local, zero external API calls require

Security & Testing Score 96/100 5 findings 126/wk Cap. Moderate
Shrike npm
A
shrike-mcp

MCP server for action governance on AI agents — 14 tools that govern tool calls, SQL queries, file writes, shell commands, and agent-to-agent messages server-side, before execution. Allow / approve / block. Session correlation. Works with Claude Desktop,

Security & Testing Score 96/100 0 findings 125/wk Cap. Moderate
S2t Mcp Accelerators npm
A
s2t-mcp-accelerators

MCP server with 36 enterprise tools: vector embeddings, CloudFormation/DynamoDB generation, OAuth/IAM/MFA validation, error analysis, data lake readiness, agent orchestration, resilience patterns, stakeholder interviews, and 12 ACI governance tools for AI

Security & Testing Score 96/100 0 findings 112/wk Cap. Moderate
Httptoolkit npm
A
httptoolkit-mcp

MCP server for HTTP Toolkit - intercept, inspect, and debug HTTP traffic via AI assistants

Security & Testing Score 96/100 1 finding 108/wk Cap. Moderate
Bastion npm
A
mcp-bastion

Reliability + security proxy for the Model Context Protocol (MCP): self-healing connections, runtime tool-security (rug-pull/poisoning detection), and a compliance-mapped audit trail.

Security & Testing Score 96/100 1 finding 103/wk Cap. Moderate
Bugherd npm
A
bugherd-mcp

MCP server for BugHerd integration - manage bugs and feedback from AI assistants

Security & Testing Score 96/100 1 finding 91/wk Cap. Moderate
Conkurrence npm
A
conkurrence

One command. Find out if your AI agrees with itself. Statistically validated consensus measurement using multi-model AI raters.

Security & Testing Score 96/100 1 finding 86/wk Cap. Moderate
Ghosthunt npm
A
ghosthunt

Find and fix every leaked secret on your machine — API keys in .env files, shell history, and configs. Scan, auto-fix, verify.

Security & Testing Score 96/100 2 findings 85/wk Cap. Moderate
Usevynix npm
A
@usevynix/mcp-server

Model Context Protocol server that exposes Vynix annotations to AI coding agents.

Security & Testing Score 96/100 0 findings 84/wk Cap. Moderate
Agent Receipts npm
A
@agent-receipts/mcp-server

Local-first MCP server for Agent Receipts — storage, engine, and protocol

Security & Testing Score 96/100 0 findings 80/wk Cap. Moderate
Depshield npm
A
depshield-mcp

MCP server for real-time dependency security — checks packages against CVE databases before your AI coding agent installs them. Works with Cursor, Claude Code, Windsurf, and any MCP-compatible IDE.

Security & Testing Score 96/100 1 finding 79/wk Cap. Moderate
Securecode npm
A
@securecode/mcp-server

SecureCodeHQ MCP Server - Let Claude Code access your secrets securely

Security & Testing Score 96/100 0 findings 78/wk Cap. Moderate
Vigile npm
A
vigile-mcp

MCP server for Vigile AI Security — query trust scores for MCP servers and agent skills from within Claude Code, Cursor, and other AI agents

Security & Testing Score 96/100 0 findings 77/wk Cap. Moderate
Clarvia npm
A
clarvia-mcp-server

MCP quality scanner and tool discovery for autonomous agents. Search 27,843+ indexed tools, check AEO (answer-engine-optimization) readiness scores, validate MCP server quality, find alternatives — the standard tool-validation layer before any agent calls

Security & Testing Score 96/100 0 findings 76/wk Cap. Moderate
Mailbuttons npm
A
@mailbuttons/mcp-server

Mailbuttons MCP stdio server + Claude Code skill for the governed Agent Mail API (sandbox-by-default, human-in-the-loop escalation). The remote MCP endpoint is served natively by the Mailbuttons backend.

Security & Testing Score 96/100 1 finding 73/wk Cap. Moderate
Local Kms npm
A
local-kms-mcp-server

Production-ready MCP server for secure per-agent key management (Ed25519, ECDSA, and more) with a local file-based keystore.

Security & Testing Score 96/100 0 findings 72/wk Cap. Moderate
Hyperd npm
A
hyperd-mcp

MCP server for hyperD x402 paid DeFi APIs — pay per call ($0.005–$1.50 USDC on Base), ~2s settlement, no API keys. 24 paid tools across 7 EVM chains, including 6 premium synthesis verdicts (Haiku 4.5 composed: risk audit, token archetype, wallet thesis, t

Security & Testing Score 96/100 0 findings 58/wk Cap. Moderate
Npm Plus npm
A
mcp-server-npm-plus

MCP server for npm — search packages, check bundle sizes, scan vulnerabilities, compare downloads, and inspect dependencies

Security & Testing Score 96/100 0 findings 56/wk Cap. Moderate
Rog0x Api Tools npm
A
@rog0x/mcp-api-tools

HTTP/API testing tools for AI agents via MCP

Security & Testing Score 96/100 1 finding 55/wk Cap. Moderate
Turbopentest npm
A
@turbopentest/mcp-server

MCP server for TurboPentest — AI-powered penetration testing from your coding assistant

Security & Testing Score 96/100 0 findings 55/wk Cap. Moderate
Aim Guard npm
A
aim-guard-mcp

AIM MCP Server :: Guard and Protect your MCPs & AI Chatting

Security & Testing Score 96/100 1 finding 53/wk Cap. Moderate
Doppler npm
A
mcp-doppler-server

Model Context Protocol server for Doppler secret management

Security & Testing Score 96/100 0 findings 52/wk Cap. Moderate
Entropy0 npm
A
@entropy0/mcp

Entropy0 MCP server — source trust and URL safety tools for AI agents

Security & Testing Score 96/100 0 findings 50/wk Cap. Moderate
Mcpwatch npm
A
mcpwatch-mcp

MCP server that audits other MCP servers. Run MCPWatch security scans from inside your Claude Code / agent loop with 10 OWASP MCP Top 10 checks.

Security & Testing Score 96/100 0 findings 46/wk Cap. Moderate