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.
MCP Server for software testing, test case management, test execution, and defect tracking.
MCP Server for AgentRadar — AI agent trust scoring and verification (ERC-8004 + EAS, x402-payable)
The testing library you need to test your MCP servers
Fidensa AI certification authority -- MCP server for trust-aware tool selection
MCP server and CLI for all eleven Kinetic Gain Protocol Suite specs + DefenseTech 6-pack tooling. One Claude Desktop config, 71 tools (47 spec + 16 implementation-preview + 8 DefenseTech): AEO Protocol, Prompt Provenance, Agent Cards, AI Evidence Format,
Bitwarden/Vaultwarden MCP server — BYOK vault access with 6 tools, Send-based reveal, TOTP, and safe agent-write
Local encrypted vault MCP server. AES-256-GCM + Argon2id. Resolves {{PLACEHOLDER}} secrets at runtime so LLMs never see real API keys. Works with Claude Desktop, Cursor, Continue.dev, Cline, Open WebUI.
MCP server for James Bloom MockServer - create expectations, verify requests, and manage mock state
Grounded quant finance math for AI agents over MCP. LLMs drift 5-30% on Black-Scholes Greeks and silently fail at Kelly, Sharpe, and VaR — this server is deterministic, citation-tested math (Hull, Wilmott, Lopez de Prado). 63 calculators (options pricing,
MCP server for SkillsSafe — AI agent skill security scanner. Detects prompt injection, credential theft, zero-width character attacks, and ClawHavoc malware. Free, no API key required.
Prompt injection detection + PII anonymization MCP server for AI agents, with a signed audit trail. Deterministic verdicts (CLEARED/ANONYMIZED/BLOCKED), 22 signatures, 7 languages. Every request returns a SHA-256-signed audit record — GDPR Art. 30 evidenc
Scan, export, and import your AI ecosystem across tools. Discover MCP servers, context files, skills, memories. Export/import between Claude, Cursor, Windsurf, Copilot, Gemini, Codex, OpenCode. CLI + MCP server.
MCP server for MailSink: programmatic temporary email inboxes for AI agents and test automation.
MCP server for agentvet: validate LLM-generated tool-call args before execution. Returns a typed error with an LLM-friendly retry hint when the args don't match.
MCP (Model Context Protocol) server for QMetry Test Management for Jira Cloud (QTM4J) REST API — exposes test case, cycle, execution, plan, folder, and automation tools.
Policy-based MCP tool call proxy
Model Context Protocol (MCP) server for AgentPay — gives AI assistants the ability to create payment intents, verify settlements, and look up AgentPassports
MCP server for ai-scanner — scan codebases for LLM usage, AI frameworks, and exposed secrets
MCP server for Volta Notes — create and read burn-after-read encrypted notes and secrets on the Internet Computer
MCP server for AgentSeal — tamper-proof audit trails for AI agents
MCP server that lets Claude, Cursor, LangGraph, and other agents record AI decisions to a tamper-evident ledger.
EU AI Act compliance audit trails and evidence generation for AI agent systems — risk classification, decision logging, gap analysis, and auditor-ready evidence packages
MCP server for VisualQ — qa profile (44 tools): run_full_audit, VRT/FRT, tracking proof, investigation ladder, rolling health
MCP server for SkillProof — ask whether a Claude Code skill was actually tested, and whether it works, before you install it.