Security MCP servers

A local receipt and approval gate for AI agent sessions. The agent can act, but it cannot sign.

Real, live npm/PyPI docs and OSV.dev vulnerability data for AI coding agents. No fake data.

Audit AI skill safety before you ship. Static, semantic, adversarial, supply chain scans.

Model inventory and governance: trace deployed models and their dependencies as an append-only log

Codebase analysis: dependency graphs, security scanning, and refactor plans for GitHub and GitLab.

AI pentester for PRs — finds exploitable bugs and hands your developer agent the fix.

The agent switchboard: identity, policy, loop-guard, and an append-only audit ledger.

MCP server for the @agentutility prooflayer cluster — pay-per-call x402 tools, no API keys, USDC…

Hard spend cap, OS sandbox, and signed receipts for unattended coding agents like Claude Code.

Read-only MCP server for SIMA Solana AI agent protection discovery. No API keys required.

Passive security scanner: audits MCP servers against the OWASP MCP Top 10, graded A-F.

Verification and trust checks for AI agents: validate, screen, propose, accounts, usage.

Early access - AI governance gateway for MCP tool calls (policies, PII masking, audit).

Real-time exploit-exposure risk check for EVM wallets, paid per query via x402 (USDC on Base).

Tamper-proof audit trail for AI agents. Signed receipts, offline-verifiable, zero backend.

Scan Solana/Anchor code against the Solana Security Standard and serve the ruleset to MCP clients.

Detects leaked secrets (API keys, tokens, private keys) in source code.

Tamper-evident, SHA-256 hash-chained audit trail and observability for AI agents.

11-scanner SAST/DAST MCP server with closed-loop remediation, SBOM/SARIF, and CI integrations

Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.

Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.

Local guardrail proxy that blocks destructive MCP tool calls, rug pulls, and tool poisoning

Multi-agent LLM security layer detecting prompt injection and jailbreaks.

Portable signed records for agent, API, MCP, and cross-runtime interactions.

AI-powered OSINT agent & MCP server. 16 tools: email, breach, IP, WHOIS, DNS, Shodan, GitHub & more.

Cordon for MCP. Security gateway with policy enforcement, audit log, and HITL approvals.

Microsoft 365 administration via Graph API application permissions (read-only by default).

BYOK vault, provider API key guidance, usage visibility, and SkillFM Beacon checks for MCP agents.