"Free APIs and services without commercial fees" matching MCP servers:

An MCP execution layer that lets capable AI models safely control a developer workstation for file edits, terminal and process execution, Git operations, language-server analysis, browser and Windows UI automation, media processing, job/resource control, and checkpointing. It also coordinates durable single- or multi-agent tasks across providers with leases, dependency graphs, evidence logs, repair loops, and separate verification gates.

Enables a Claude Code cloud session to run shell commands inside a chroot jail on your own computer and to call the MCP servers already installed there, with every request authenticated and relayed over a Cloudflare quick tunnel so no router port is opened and no SSH key or tunnel is ever handed to the cloud VM.

Enables managing a parametric CLI command registry with profile isolation and pipelines from Cursor agents via 11 MCP tools.

Enables AI clients to securely execute remote commands and transfer files over SSH through standardized MCP tools, with multi-host management, flexible authentication, and an admin console.

Combines KC Chat Panel session interaction with AgentDock computer control tools, enabling Cursor Cloud Agent to chat and operate the local machine via AgentDock.

Enables agents to discover and inspect an installed qxctl command registry, run read-only operations, and preview/apply explicitly enabled administrative actions while preserving native authority, receipts, and recovery rules.

MCP server for managing Ubuntu servers over SSH. Enables Claude to check system health, inspect services, tail logs, review updates, and run commands remotely.

Enables Claude to create and interact with real, persistent Windows terminal sessions (cmd.exe or PowerShell) through ConPTY, including sending commands, reading output, and scoped Ctrl+C interrupts without affecting other processes.

Enables AI to execute registered system commands across platforms using a stable program + args interface, without requiring shell-specific syntax or tool discovery.

Enables AI assistants to monitor and manage Linux infrastructure including services, logs, processes, disk, memory, ports, cron, nginx, Docker, and system health checks via the Model Context Protocol.

Connects AI tools to local dev servers, enabling them to view pages, call APIs, read/edit files, and run commands with safety guardrails.

Enables agents to inspect ROS topics, processes, tmux sessions, and logs, and to perform operational actions such as sending tmux commands, restarting services, executing commands in containers, and running SSH remote commands.

Lets MCP-capable AI clients run commands and manage files on remote machines over SSH without installing anything remotely.

An MCP server that reports on and manages systemd services using systemctl and journalctl, enabling service listing, status, logs, and control operations.

A credential-free MCP server offering developer utilities such as JSON formatting, regex testing, hashing, UUID generation, base64 transforms, and JWT inspection, with no network dependencies.

Enables AI agents to communicate and coordinate across tmux panes, allowing them to read, type, and send messages to each other without manual copy-pasting.

Zero-config SSH/SFTP MCP server that lets an LLM client open temporary SSH/SFTP sessions to remote hosts, run commands, and upload/download files without holding any pre-baked credentials.

Linux system administration via AI agents — MCP server for managing services, processes, disk, network and logs on Linux systems.

Enables sudo-free management of /etc/hosts entries for Hack The Box and lab work, with a zero-dependency MCP server for AI coding agents.

Enables natural language SSH server management via Claude Code, allowing users to read logs, check services, run commands, and transfer files across multiple servers.

An MCP server that lets an AI assistant run commands and transfer files over SSH without exposing connection details.

Provides AI coding agents with structured, evidence-based diagnostics about the local development environment, detecting tech stack, runtime mismatches, dependency state, services, ports, and Git status without exposing secrets or using network calls.

A local-first secrets vault for MCP clients that lets AI assistants use secrets by injecting them into child processes, without the plaintext ever entering the model's context.

Enables executing shell commands without permission prompts, including running commands and managing background processes.

Enables MCP-compatible AI clients to interpret the init-app CLI, explore its supported blueprints, and translate natural-language project requirements into validated command arguments without executing the CLI.

Enables controlling robots in ROS environments through natural language, supporting topics, services, actions, and GUI tools.

Provides read-only access to systemd units, failed units, timers, unit status and files, journal entries, boots, and system summaries through eight queries. Enables inspection and triage of systemd services without granting write access or shell execution.

Provides a governed command plane for MCP agents to manage PostgreSQL databases, SSH sessions, and HTTP APIs with encrypted credential storage and prescriptive workflows.

Enables natural language interaction with Getty's Quire digital publishing tool, allowing users to perform CLI tasks like creating projects without using the terminal.

Provides Ubuntu system information (CPU, memory, disk, network, services, processes) to Bob via natural language queries.