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.

Provider Lwc Experts Official npm
A
@salesforce/mcp-provider-lwc-experts

(For Interal Use Only) Provided MCP Tools for code analysis and improvement of LWC components

Security & Testing Score 100/100 0 findings 36k/wk Cap. Minimal
Agent Toolkit Official npm
A
@stripe/agent-toolkit

The Stripe Agent Toolkit enables popular agent frameworks including LangChain and Vercel's AI SDK to integrate with Stripe APIs through function calling.

Security & Testing Score 100/100 0 findings 20k/wk Cap. Minimal
Auto Mobile Source verified 2 implementations
A
best: @kaeawc/auto-mobile

Mobile device interaction automation via MCP

Security & Testing Best score 100/100 0 findings 6.6k/wk Cap. Minimal
Testrail Source verified 7 implementations
A
best: @bun913/mcp-testrail

<a href="https://flatt.tech/oss/gmo/trampoline" target="_blank"><img src="https://flatt.tech/assets/images/badges/gmo-oss.svg" height="24px"/></a>

Security & Testing Best score 100/100 0 findings 1.6k/wk Cap. Minimal
Lighthouse Source verified npm
A
@danielsogl/lighthouse-mcp

A comprehensive Model Context Protocol (MCP) server that provides web performance auditing, accessibility testing, SEO analysis, security assessment, and Core Web Vitals monitoring using Google Lighthouse. Enables LLMs and AI agents to perform detailed we

Security & Testing Score 100/100 0 findings 1.2k/wk Cap. Minimal
Oauth Source verified npm
A
mcp-oauth-server

Self-hosted OAuth 2.1 Authorization Server for MCP servers (Express/TypeScript). Implements the MCP Authorization spec: Client ID Metadata Documents (CIMD), Dynamic Client Registration, PKCE, resource indicators, device flow.

Security & Testing Score 100/100 0 findings 792/wk Cap. Minimal
Rigour Labs Source verified npm
A
@rigour-labs/mcp

MCP server + live dashboard for AI code governance — OWASP LLM Top 10 (10/10), real-time MCP App UI, 25+ security patterns, Bayesian learning Brain, hallucinated import detection, multi-agent governance. Works with Claude, Cursor, VS Code, ChatGPT, Goose,

Security & Testing Score 100/100 0 findings 560/wk Cap. Minimal
Virustotal Source verified npm
A
@burtthecoder/mcp-virustotal

MCP server for VirusTotal API integration

Security & Testing Score 100/100 0 findings 389/wk Cap. Minimal
Vastlint Source verified npm
A
vastlint

Validate VAST 2.0–4.4, VMAP 1.0, and DAAST 1.0 ad tags against IAB specs. 212 rules. Rust/WASM core.

Security & Testing Score 100/100 0 findings 348/wk Cap. Minimal
Realm Source verified npm
A
@sensigo/realm-mcp

MCP server for Realm — exposes 7 tools for AI agent connections over stdio or HTTP.

Security & Testing Score 100/100 0 findings 229/wk Cap. Minimal
Authentik Source verified 2 implementations
A
best: @samik081/mcp-authentik

Manage Authentik through AI assistants

Security & Testing Best score 100/100 0 findings 195/wk Cap. Minimal
Testcollab Source verified npm
A
@testcollab/mcp-server

MCP Server for TestCollab - Exposes test management functionality to AI assistants

Security & Testing Score 100/100 0 findings 193/wk Cap. Minimal
Deptrust Source verified npm
A
@clidey/deptrust

Install deptrust, a local package vulnerability checker and MCP server for AI agents.

Security & Testing Score 100/100 1 finding 182/wk Cap. Minimal
Rhombus Node Source verified npm
A
rhombus-node-mcp

MCP server for Rhombus API

Security & Testing Score 100/100 2 findings 116/wk Cap. Minimal
Vikunja Source verified npm
A
@eargollo/vikunja-mcp

Security-first MCP server for Vikunja — full API coverage, read-only by default with opt-in write/delete, and just one dependency (the official MCP SDK).

Security & Testing Score 100/100 0 findings 97/wk Cap. Minimal
Cucumberstudio Source verified npm
A
cucumberstudio-mcp

MCP server for Cucumber Studio API integration

Security & Testing Score 100/100 3 findings 81/wk Cap. Minimal
Checker Source verified npm
A
@oksigenia/checker-mcp

MCP server exposing a domain security & privacy checker (SSL/TLS, email auth, DNS, web headers). Local-first, zero telemetry.

Security & Testing Score 100/100 0 findings 78/wk Cap. Minimal
Calllint Source verified npm
A
calllint-mcp

MCP server for CallLint — a static preflight safety gate for MCP servers and agent tools. Use before installing or approving other MCP servers. Never executes the server it judges.

Security & Testing Score 100/100 0 findings 70/wk Cap. Minimal
Keycloak Admin Source verified npm
A
mcp-keycloak-admin

Model Context Protocol server to administer Keycloak through its Admin REST API

Security & Testing Score 100/100 0 findings 69/wk Cap. Minimal
Security Audit Source verified 2 implementations
A
best: mcp-security-audit

Audit your package.json dependencies

Security & Testing Best score 100/100 0 findings 62/wk Cap. Minimal
Client Credentials Auth Source verified npm
A
mcp-client-credentials-auth

Local MCP server that authenticates to remote OAuth-protected MCP servers following MCP Auth Specification using client_credentials grant usefull for autonomous agents, background services, CI/CD pipelines, server-to-server integrations, and daemon proces

Security & Testing Score 100/100 0 findings 61/wk Cap. Minimal
Pictmcp Source verified npm
A
pictmcp

MCP (Model Context Protocol) server that provides pairwise combinatorial testing capabilities to AI assistants.

Security & Testing Score 100/100 0 findings 59/wk Cap. Minimal
Agentgate Source verified 2 implementations
A
best: @agentkitai/agentgate-mcp

MCP (Model Context Protocol) server for AgentGate. Enables Claude and other MCP-compatible AI assistants to request approvals.

Security & Testing Best score 100/100 0 findings 56/wk Cap. Minimal
Dechonet Source verified npm
A
dechonet-mcp

Domain security reconnaissance MCP server — 13 tools for AI agents. DNS, SSL, HTTP headers, email auth, port scan, ASN, RDAP and more. Free, no API key.

Security & Testing Score 100/100 0 findings 56/wk Cap. Minimal

Vulnerability scanners, secret vaults and browser-test rigs were built for terminals and CI pipelines; the Model Context Protocol brings them into a conversation instead. An MCP server in this category typically wraps static-analysis engines in the Semgrep family, dependency and container scanners like Trivy, web probes such as OWASP ZAP and Nuclei, secret stores like HashiCorp Vault, or QA-automation frameworks built on Playwright and Selenium — so Claude, Cursor and other AI assistants can launch scans, read results and act on them conversationally.

Running security scans and test suites through an MCP server

An assistant can scan a changed branch and rank the findings by exploitability; it can fetch a short-lived credential from a secrets manager for a test run instead of leaving keys in config files; and it can generate a browser test suite, execute it, and diagnose the flaky cases. CVE lookups during code review are a common fourth. The MCP Trust Registry lists automatically scanned servers for all of these jobs.

Picking a trustworthy vulnerability-scanning or secrets MCP server

Defensive tooling carries a built-in irony: it has the deepest reach into the system it protects. A server bridging a vault can read every secret its token can; one wrapping a scanner sees your unpatched vulnerabilities — a ready-made attack map; a scan runner can be aimed at hosts nobody authorized; a QA-automation server drives a real browser that may hold logged-in sessions. Before connecting one:

  • Grant the narrowest token possible — read-only where feasible, scoped to a single project or vault path.
  • Match the capability blast radius to the job; a test runner rarely needs broad network egress or filesystem write access.
  • Weigh the Trust Score evidence, not just the letter grade. Each grade comes from one deterministic open-source engine reading the published npm or PyPI package: identical code, identical score, no paid placement — see the scoring model.
  • Audit the neighbors too: servers in Files & Storage and Learning & Documentation often touch the same repositories and internal docs your security tooling reads, so a weak link there undermines hardening here.

Is it safe to give an MCP server access to a secrets manager?

Only with tight scoping. A Model Context Protocol server that brokers vault or CI credentials can exfiltrate whatever its token reaches, and prompt-injected tool output can steer an assistant into requesting more than intended. Issue single-purpose, short-lived tokens, and review the server's capability profile and security findings on its registry page before connecting.