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.

Auditspark npm
A
auditspark-mcp

MCP server for AuditSpark — audit any website from Claude. Scores SEO, performance, accessibility, UX, content, and 10+ other categories in under 2 minutes.

Security & Testing Score 96/100 0 findings 13/wk Cap. Moderate
Slack Enterprise 2 implementations
A
best: slack-enterprise-mcp

Slack Enterprise MCP server. Tools: send message, search messages, list channels. Built by MEOK AI Labs.

Security & Testing Best score 96/100 0 findings 13/wk Cap. Moderate
Agent Cafe npm
A
agent-cafe-mcp

MCP server for AI agents to interact with The Agent Cafe — an on-chain restaurant on Base where agents buy food tokens and receive gas sponsorship

Security & Testing Score 96/100 0 findings 12/wk Cap. Moderate
Voidsend npm
A
voidsend-mcp

MCP server for VoidSend — send and receive end-to-end encrypted messages via AI agents

Security & Testing Score 96/100 1 finding 12/wk Cap. Moderate
Agents Remote
A
https://paygent.obsmetrics.com/mcp

Pay-per-call safety guards for AI agents: injection, tool-call, signing, secret, x402-trust.

Security & Testing Score 96/100 1 finding Cap. Moderate
Certificate Monitor PyPI
A
mcp-certificate-monitor

A FastMCP server that lets an AI host monitor certificate expiry across a set of domains

Security & Testing Score 96/100 0 findings Cap. Moderate
Certindex PyPI
A
certindex-mcp

MCP server exposing CertIndex's Certificate Transparency search tools to any MCP-compatible client.

Security & Testing Score 96/100 0 findings Cap. Moderate
Clearfront PyPI
A
clearfront

Clearfront OSINT: AI-powered OSINT agent, MCP server, and CLI that maps your digital footprint across 3,400+ public data sources. Interactive REPL + 30 tools. Anthropic Claude or local Ollama. For authorized security research use only.

Security & Testing Score 96/100 0 findings Cap. Moderate
Cloud Audit PyPI
A
cloud-audit

Open-source, read-only AWS security scanner. 110 checks across 25 services, 31 attack-chain rules, 64 IAM escalation methods (incl. lateral AssumeRole graph), Proof Mode exploitability verification, data perimeter and Bedrock AgentCore checks, Blast Radius CLI, Threat Feed, What-If simulator, AI-SPM, 6 compliance frameworks, breach-cost estimation, MCP server. CLI + Terraform remediation on every finding.

Security & Testing Score 96/100 1 finding Cap. Moderate
Cvefeed PyPI
A
cvefeed-mcp

Model Context Protocol (MCP) server for the CVEFeed.io vulnerability intelligence API

Security & Testing Score 96/100 0 findings Cap. Moderate
Fedramp 20x PyPI
A
fedramp-20x-mcp

MCP server for querying FedRAMP 20x requirements

Security & Testing Score 96/100 3 findings Cap. Moderate
Jobverify PyPI
A
jobverify-mcp

Agentic MCP server for detecting fake LinkedIn recruiter / job-offer scams using free OSINT sources

Security & Testing Score 96/100 0 findings Cap. Moderate
Mipiti PyPI
A
mipiti-mcp

MCP server for Mipiti — AI-powered security posture platform

Security & Testing Score 96/100 0 findings Cap. Moderate
Oj PyPI
A
oj-mcp-server

MCP server for an Online Judge

Security & Testing Score 96/100 0 findings Cap. Moderate
Opencti PyPI
A
opencti-mcp

MCP server exposing the OpenCTI threat-intelligence platform to AI assistants.

Security & Testing Score 96/100 0 findings Cap. Moderate
Openosint PyPI
A
openosint

AI-powered OSINT agent, MCP server, and CLI. Interactive REPL + 16 tools. Anthropic Claude or local Ollama. For authorized security research use only.

Security & Testing Score 96/100 3 findings Cap. Moderate
Plurity PyPI
A
plurity-mcp

Unified MCP server for all Plurity services (Audit, Toll, Intelligence)

Security & Testing Score 96/100 1 finding Cap. Moderate
Synpareia Trust PyPI
A
synpareia-trust-mcp

Trust tools for agent-to-agent dealings — prove, vet, and bind with verifiable evidence (MCP server)

Security & Testing Score 96/100 0 findings Cap. Moderate
Terminal Control PyPI
A
terminal-control-mcp

Terminal Control MCP Server

Security & Testing Score 96/100 1 finding Cap. Moderate
Threatlocker PyPI
A
threatlocker-mcp

MCP server for the ThreatLocker Portal API

Security & Testing Score 96/100 0 findings Cap. Moderate
Vuln Intel PyPI
A
vuln-intel-mcp

Local MCP server for CVE remediation intelligence from public sources (NVD, CISA KEV, FIRST EPSS). Your model does the reasoning — no API keys, no external LLM calls, no data leaves your machine.

Security & Testing Score 96/100 0 findings Cap. Moderate
Webhook Ai PyPI
A
webhook-ai-mcp

Webhook Ai tools for AI agents. Capabilities: validate webhook signature, log webhook event, replay events. Built by MEOK AI Labs.

Security & Testing Score 96/100 0 findings Cap. Moderate
Hackle npm
A
@hackle-io/hackle-mcp

Model Context Protocol server for Hackle

Security & Testing Score 95/100 0 findings 520/wk Cap. Moderate
Evermint npm
A
evermint-mcp

MCP server for EverMint, tamper-evident proof layer for AI agents

Security & Testing Score 95/100 0 findings 70/wk Cap. Moderate