Security MCP servers

Agents pay for work and prove it. Verified checks $0.15, recovery $1.00. USDC on Base via x402.

AI-powered codebase analysis — call graphs, security, dead code, complexity. 150+ tools.

Extract regular expressions from code, each with a ReDoS safety verdict.

Query devices, alerts, syslog, Suricata IDS, NetFlow and captures on your Netmon appliance.

Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.

Unofficial MCP server for the Bitwarden Public API and Secrets Manager, self-hosted or cloud.

Checks a Markdown folder's OKF frontmatter tier, locally. No-egress is a vendor claim: see README.

Deterministic security scan of MCP servers, agent skills and npm/PyPI packages. Runs locally.

macOS OpenVPN/FortiGate VPN status, logs and diagnosis; read-only by default, never returns secrets

Offline security scanning for AI-generated code: seven open-source scanners in one MCP server.

Reverse engineering and security analysis of .NET and native binaries: decompile, compare, patch.

The record layer for the machine age: counter-signed receipts and agent action records.

Needs the PrivacyFence app from privacyfence.eu: human approval and audit for AI access to your data

Policy enforcement plane for MCP: every tool call ends in a verdict. Self-hosted, MIT.

Post-quantum readiness of any website, PQC adoption figures, the probe map; paid checks via x402.

Verifiable agent work contracts; separate opt-in Codex preview-directory guard.

Drafts a network allow list for agent tools and runs them in a network-blocked sandbox.

Sanctions, crypto wallet, email and IP screening for agents. Pay per check in USDC via x402.

Checks every MCP tool call of your agent with an independent witness and gives signed receipts.

Juniper Security Director Cloud MCP server: scoped, audited change control. Rust.

Local crypto inventory for developers and AI agents; coverage and limits inside the CBOM.

Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance.

One MCP endpoint for all your servers: a few meta-tools, Keychain secrets, sandbox, audit, OAuth.

Retrieve CVEs and index them inside your codebase. One SQLite+FTS5 index, one CLI, one MCP server.

MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.

MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt

Find what a repository's CI is missing, and which security checks cannot fail the build.

MCP server for Portveil: let AI assistants see your devices and move them between VPN locations.