"Marking Linux terminal commands as safe or unsafe for local execution" matching MCP servers:

MCP server that provides local, de-identified access to a demo EMR database using a private LLM for de-identification, ensuring raw patient data stays local.

An MCP server that governs AI agent commands to physical robot arms, enforcing Asimov's Three Laws through Cedar authorization policies to prevent unsafe actions.

A secure terminal execution server that enables controlled command execution with security features and resource limits via the Model Context Protocol (MCP).

Turns OpenAPI specs into MCP tools with secure defaults, risk inspection, confirmation gates, response limits, audit logging, and secret redaction.

A deterministic guard layer that blocks unauthorized tool calls and validates arguments before execution, preventing tool poisoning and jailbreak attacks on MCP servers.

A safe gateway to convert OpenAPI specs into MCP tools with secure defaults, risk inspection, and confirmation gates.

Enables AI assistants to encrypt and decrypt files or text using the SAFE utility with support for passwords, public keys, and GitHub usernames. It provides tools for key generation, identity listing, and inspecting encrypted file metadata.

Enables Claude AI to play a cookie-themed dungeon RPG, including clicking cookies, recruiting heroes, exploring dungeons, and managing inventory through natural language commands.

An MCP server that enables AI agents to securely add secrets to .env files by prompting the user to input the value through a local masked dialog, ensuring the agent never sees the secret.

Enables LLMs to propose UPDATE/DELETE SQL that is run in a transaction, measured, and rolled back, requiring human approval before applying to prevent unauthorized changes.

Enables Codex to safely interact with Bitwarden vault status, metadata, generated logins, folders, and approved automation profiles while preventing direct secret access.

MCP server enabling AI agents to use secrets (API keys, tokens) via encrypted vault, executing HTTP/shell/SSH actions server-side while never exposing secret values to the AI.

MCP server that safely fixes npm audit vulnerabilities by planning, applying fixes one at a time, running tests after each, and auto-reverting failures to prevent breaking changes.

A fail-closed policy boundary that translates local stdio MCP clients to authenticated Streamable HTTP servers, enforcing allowlists or read-only modes and redacting credentials from audit trails.

Provides access to 30+ Kali Linux penetration testing tools including Nmap, SQLmap, Metasploit, and others for authorized security testing, vulnerability scanning, and network reconnaissance through Claude Desktop.

Enables AI agents to read local business data and request database mutations, while requiring human approval before updates or deletions are executed. It provides read-only tools, approval workflows, and audit logging to prevent autonomous destructive changes.

A local MCP server that provides controlled repository access with policy-based file filtering, secret redaction, and audit logging for AI coding agents.

Enables cloud-based MCP clients to delegate privacy-sensitive or large-output tasks to a local LLM, returning sanitized placeholders or digested summaries so private data never leaves the user's network.

Local-first Gmail MCP server using PKCE + loopback OAuth flow that stores refresh tokens in the OS keychain, enabling secure read/write Gmail access via MCP tools without tokens leaving the device.

Enables a cloud orchestrator to query a local Ollama model over Tailscale or a LAN as a side-channel for drafts, summaries, and other helper output, with tools to list available models and to redact text. Answers leaving the server are passed through output-only DLP that masks card numbers, IBANs, emails, phone numbers, API keys, and similar secrets before they reach the cloud.