"GNOME Terminal" matching MCP servers:

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

Local credential broker for AI agents: they call HTTP APIs, SSH, SFTP and databases through allow-listed presets while secrets stay in the OS keychain. Per-preset approval (desktop, terminal or Telegram) and an append-only audit log.

Terminal-native DOM perception layer for AppSec and AI. Hook into live Chrome sessions, compress HTML tokens by 98.9%, and map attack surfaces deterministically.

Order limits, human approval (terminal or Telegram), a kill switch and a hash-chained audit log in front of any broker or exchange MCP server. Verified profiles for Alpaca MCP and CCXT MCP.

Enables local privacy scanning and masking of secrets and PII, verifies test-suite integrity to prevent silent fake success, and inspects or blocks destructive terminal and SQL commands before execution.

Enables evolving scan and policy configurations by inferring security phenotypes from observed findings, seeding competing genomes, measuring fitness, and generating bounded trial plans with ancestry lineage.

Enables AI assistants to perform penetration testing by running real Kali Linux security tools and returning structured, verified findings instead of raw terminal output.

A specialized MCP server for Claude Desktop that allows executing terminal commands for malware analysis with support for common analysis tools like file, strings, hexdump, objdump, and xxd.

Security gateway for MCP tool calls. Sits between your LLM client and MCP servers, enforcing per-tool policies (allow/block/approve/read-only), logging every call, and pausing dangerous operations for human approval in terminal or Slack.

Enables AI clients to remotely access and operate granted machines, executing file, search, write, and terminal operations relayed by an outbound agent. Access is default-deny and revocable: each client–device pair needs an explicit panel-issued grant, with presets, directory/command guardrails, and human approvals.

Gives a remote MCP client one read-only tool for asking a locally running Hermes Agent short questions, answered with that machine's own memory and session context, over bearer-authenticated Streamable HTTP. It exposes no terminal, file writes, messaging, or other action capability, and every other request is refused upstream of the model.

Aggregates multiple backend MCP servers (Stdio, SSE, and Streamable HTTP) into a single hub, exposing their combined tools and resources through unified SSE or Streamable HTTP endpoints, or as a Stdio server, while routing requests to the correct backend. Adds API-key/bearer-token endpoint security, per-tool enable/disable and renaming, and an optional web admin UI with live config reload, install monitoring, and a web terminal.

Enables agents and terminal workflows to run calibrated, typed single-pass evaluations such as diff review scoring, acceptance gating, command safety screening, candidate selection, and claim verification. Returns compact structured verdicts with numeric confidence scores in place of verbose chat responses.

Enables users to pair the official ChatGPT mobile app with a local Codex CLI session, check connectivity, list or revoke paired devices, and enable or disable remote access through terminal or conversational commands.

Connects MCP clients to a Kali Linux terminal API, enabling AI-assisted penetration testing, CTF challenge solving, and automated security reconnaissance through command execution.

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

Enables controlled diagnostics and limited actions on a VPS through safe, auditable tools instead of an unrestricted root terminal, including read-only checks, basic Docker status, allowed-path file reading/searching, and YAML/JSON validation.

Production-grade MCP gateway that provides controlled access to the Bloomberg Desktop API on a Windows terminal via Tailscale, with policy, quotas, and audit safety.

Enables malware analysis through terminal command execution with specialized tools including file type detection, string extraction, hexdumps, and disassembly operations. Provides process management with configurable timeouts for safe analysis workflows.