Search

Enforce rules on AI coding agents — guardrails that run outside the context window, so they survive context rot, compaction, and agent amnesia.

Open-source MCP proxy for AI agent access control with CEL policies, RBAC, and audit.

🐍 🏠 - A Model Context Protocol (MCP) server for querying the CVE-Search API. This server provides comprehensive access to CVE-Search, browse vendor and product、get CVE per CVE-ID、get the last updated CVEs.

Plugsight MCP server — the agent-facing peer of the menu-bar app (docs/spec/03). A deliberately thin stdio-MCP adapter over the daemon's local JSON-RPC-over-UDS API (docs/spec/02).

MCP Server for dependfix: expose scan/fix capabilities to AI assistants

Lilith MCP Middleware SDK

Drop-in auth gateway for self-hosted MCP servers, API-key auth, per-tool allowlists, rate limiting & audit logs, with zero upstream changes. Single Go binary.

Permissions that learn how you work. LeastGrant watches what your coding agents normally do, lets the routine flow, and stops the weird stuff.

Webhook signature-verification audit. Stripe, GitHub, Shopify, Twilio +17. Local. Deterministic.

MCP server for remote SSH operations -- persistent sessions, structured command execution, SFTP file transfer, and port forwarding for AI agents.

macOS menu bar privacy proxy between Claude (MCP) and your personal data

Find Node.js API routes with no auth check or input validation, and scan project health.

Dependency-free static analyzer that audits LLM agent tool/function definitions (OpenAI, Anthropic, MCP) for excessive agency, code-execution & SSRF sinks, secret access, and data-exfiltration surface — mapped to the OWASP 2025 LLM Top-10. Runs in CI.

ghidraMCP enables LLMs to autonomously reverse engineer applications by integrating Ghidra's decompilation and analysis tools with MCP clients.

WHOIS/RDAP, DNS, SSL, live subdomains with IPs, and SPF/DMARC/DKIM for any domain.

[](https://glama.ai/mcp/servers/creatorrmode-lead/avp-sdk) 📇 ☁️ - Trust, identity (W3C DID), and EigenTrust reputation for AI agents. Attestations, disputes, sybil detection, IPFS audit anchoring.

Offline text-to-speech via VoxCPM2 — 30 languages, voice design, voice cloning. Runs locally on Apple Silicon.

Zero-dependency, in-memory PII & secrets redaction SDK for Node.js, Next.js, OpenAI, and LangChain. 100% client-side & server-side zero-trust prompt anonymization under 1ms.

DefectDojo MCP server for integrating with DefectDojo vulnerability management system

Credential isolation for AI agents. Inject secrets at the network boundary.