Search

Agente local y gateway MCP para Windows: acceso controlado de asistentes de IA a tu PC, con aprobaciones firmadas, auditoría a prueba de manipulación y sin puertos abiertos. MPL-2.0.

A local, safe-by-default AI risk guard for high-risk commands — deterministic rules plus the Laya decision model. Defense-in-depth for the dockndevai MCP suite; the guard only tightens.

MCP server providing a restricted Python execution tool

Read-only MCP server for OctoWatch DLP Cloud (console analytics, monitoring, risks, productivity)

Give your AI agent new tools without giving it your API keys. Sandboxed Lua commands, a key vault, and an MCP server built in.

GameDay testing for MCP servers — the oracle is the wire, not the scoreboard.

⚠️ Pre-release — wait for 1.0.0 before relying on this. Currently under active development; APIs and behaviour may change without notice. SPYS MCP client — local stdio bridge + reverse tunnel for AI-driven pentest tools (Claude Code, Cursor, etc).

Official Model Context Protocol (MCP) server for @blursec/sdk — lets AI agents check credentials, tokens, and sessions against live stealer-log threat intel.

[](https://glama.ai/mcp/servers/srbsa/diffgate) 📇 🏠 🍎 🪟 🐧 - Deterministic guardrail for AI-written diffs, runnable from inside the coding agent's own loop over MCP. Zero-LLM-token, AST-precise rules (SQLi, SSRF, XXE, permissive CORS, prototype pollution, hardcoded secrets) across 8 languages, plus structural checks for reinvented helpers and over-abstraction — findings scoped to only the changed lines,

Open-source, self-hosted, versioned vault for AI-generated HTML, Markdown, Mermaid, and image artifacts, with scoped MCP access and isolated two-origin previews.

Unified threat intel - OTX, AbuseIPDB, GreyNoise, abuse.ch, Feodo Tracker

MCP server that scans files and directories for exposed secrets, API keys, and credentials

Trust verification gateway for MCP — policy enforcement, approval workflows, and audit logging for agent-tool connections

Temporary package placeholder for staged publishing

Deterministic policy engine for AI agent tool calls: parse, sign, verify and evaluate AgentLaw policy manifests. No MCP dependency — embeddable anywhere.

A local filesystem MCP server that lets LLMs and AI agents read, write, search, diff, patch, and manage files safely and efficiently. Built for reliable, structured, and controlled filesystem interaction.

A fuse for autonomous agents, exposed over the Model Context Protocol. Ask it whether an action is safe before you take it.

A MCP server for running sandboxed scripts

Local-first egress hygiene for MCP servers: capture, diff, and allowlist what your AI-agent tools contact on the network.

MCP server for Unplug — LLM defense layer for Claude Code, Cursor, and more