Security MCP Servers

Python client for kb0 — the knowledge base layer for AI agents (MCP, markdown, git).

Zero-dependency security linter for MCP (Model Context Protocol) configurations

Scan MCP and AI agent configs for risky permissions, secrets, unsafe commands, and CI safety gaps.

Redacts common secrets, email addresses, and phone numbers.

Agents message each other and partners' agents. Claude Code, Codex (beta): memory, board, key vault.

Find unflagged agent OAuth clients before the mandate lock — signed per-client census verdicts.

Model Context Protocol (MCP) server for Password Pusher (pwpush).

7 x402 v2 pay-per-call MCP tools for FDA/ChEMBL, token rug scan, Base escrow & wallet forensics.

See Everything. Undo Anything. Test Anything Safely. — Security middleware for AI agents.

MCP Firewall Proxy — policy-based tool access control using NAIL effects

MCP server for PingCastle Enterprise — query AD/Entra security reports, findings, comparisons, and scans from your LLM

LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.

Fjordova MCP gateway for Fortnox accounting data and tools, with OAuth-based user authorization.

Create and manage GDPR-compliant, EU-hosted forms from any MCP-compatible AI assistant.

Memory Vault MCP Server — Markdown + SQLite knowledge store with bidirectional [[wikilinks]] for AI agents

Privacy Vault Protocol for MCP: tokenize sensitive data before the LLM sees it

Runtime behavioral auditor for MCP servers — strace-based scope-violation detection

Real-time FIRST.org EPSS 30-day CVE exploit probability scoring and OSV package security audit.

Man-in-the-middle proxy for the Model Context Protocol: intercept, inspect, and tamper with MCP traffic (and its OAuth flows) through Burp Suite.

Sift MCP Server — Agent Execution Governance for Claude Desktop and other MCP clients

Linux only, local: post-quantum CBOM scan, encrypt to public keys, verify. Takes no secrets

Inspects live IPv4/IPv6 DNS resolution, TLS certificate issuer/expiry, and HTTP security grade.

Queries ArXiv for AI/CS/math papers and returns structured abstracts, authors, PDF links, and Bib.

Security scanner for AI agents and MCP servers: injection, jailbreak, tool abuse.