"Top 100 MCP Servers Ranked by Weekly Downloads" matching MCP servers:

This read-only MCP Server allows you to connect to SAP Sybase data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for SAP Sybase (https://www.cdata.com/drivers/sybase/download/mcp).

An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like DeepSeek, GLM, and Qwen.

Mac file and terminal tools for local AI clients, plus an opt-in ChatGPT Developer Mode relay. Checked edits, bounded reads and real exit codes. Free MIT agent; OpenAI listing under review. Owner-level access, not a sandbox.

A Model Context Protocol (MCP) server with HTTP transport that implements JWT authentication, allowing secure tool execution and prompt handling with role-based access control.

Enables ChatGPT to control multiple registered Windows devices through a self-hosted gateway, routing Desktop Commander tool calls to specific workers by device ID.

An MCP server that solves permission fatigue by letting you pre-approve commands, enabling Claude to run them without asking for permission each time.

Enables SSH command execution, file uploads/downloads, and multi-server management with zero-config inline credentials, supporting async jobs and AI-readable output.

Provides AI agents with an unrestricted VPS root shell by executing arbitrary shell commands and returning structured results such as exit code, stdout, stderr, timeout, and truncation status.

A hardened suite of two MCP servers — a terminal command executor and a file organizer — built on one shared, deny-by-default safety core.

Enables AI assistants to call any CLI tool by scanning its help output and serving it as an MCP server.

Enables LLMs to interact with Discord channels by sending and reading messages through Discord's API, with a focus on maintaining user control and security.

An MCP server that publishes CLI tools on your machine for discoverability by LLMs

A minimal MCP server that executes commands on remote hosts by delegating to the local ssh binary, supporting batch-mode execution and optional timeout.

Enables terminal and filesystem capabilities through local stdio or remote device modes, backed by a contract and validation layer.

Turns any command-line tool into an MCP server by parsing its --help, enabling AI assistants to discover and safely invoke CLI tools with validation, allow-listing, and sandboxing.

Bypasses Claude Desktop sandbox network restrictions by providing tools to fetch any URL, execute network-capable CLI commands (yt-dlp, curl, ffmpeg), and read files created by those tools.

Enables AI assistants to interact with serial port devices by sending commands, capturing output, and managing connections, with real-time browser-based terminal monitoring.

Multi-threaded terminal management MCP server for AI assistants, enabling async command execution, batch operations, and real-time web monitoring with up to 100 concurrent terminals.

Provides persistent SSH access to servers using OpenSSH ControlMaster multiplexing, allowing AI agents to run commands on registered hosts by name without re-entering credentials.

Remote MCP / x402 / USDC / Base / Solana / OpenAPI / Google ADK / Gemini Xcatcher is an agent-first Remote MCP server (Streamable HTTP) for high-throughput crawling of fresh/latest posts across large sets of X (Twitter) usernames. It supports x402 pay-as-you-go top-ups using USDC on Base and Solana.

Enables AI clients (ZCode, Claude Code, Codex, Cursor, Cline) to run shell commands, manage background jobs, and stream files to and from remote Linux servers over SSH through a single authenticated MCP gateway. Target machines' SSH port stays closed to AI and the internet, with token whitelists, command blacklists, confirmations, and audit logging layered on top.

Connects MCP clients to a Kali Linux terminal for AI-assisted penetration testing and CTF challenge solving by executing commands like Nmap, Metasploit, and custom scripts.

Connects LLMs to a Kali Linux host over SSH for authorized penetration testing, exposing tools organized by pentest phases (recon, enumeration, exploitation) with scope guardrails.

A secure Docker-based environment that allows AI assistants to safely execute code without direct access to the host system by running all code within isolated containers.

MCP server to perform various OSINT tasks by leveraging common network reconnaissance tools.

Interactive, streaming SSH tool for LLM agents that enables spawning long-running remote commands with live line-by-line output, signal handling, stdin input, and SFTP file transfer.

Enables AI agents to securely use real secrets (API keys, database passwords) by requiring human approval for each release, ensuring secrets never enter the model's context.

Infrastructure access broker for AI agents — SSH & Kubernetes. Per-operation ephemeral credentials minted by a separate signer; the model never touches one. MCP stdio / HTTP+OIDC.

Offline server that explains any shell command token-by-token and flags destructive ones (rm -rf /, curl | sudo bash, dd/mkfs/shred to a disk device, chmod -R 777 /) — a safety gate for agentic shell execution.

Enables LLMs to perform live debugging, dump analysis, and remote debugging by exposing Microsoft CDB capabilities through MCP. It manages cdb.exe sessions, forwards commands, and returns raw debugger output.