"Shell" matching MCP servers:

Enables executing sbt commands in a persistent shell session for Scala projects, avoiding startup overhead.

Cross-platform command execution server that intelligently adapts shell commands to the operating system and detects project-specific package managers (npm/bun, pip/poetry), with runtime-editable command mappings per project.

Provides a stateful Django shell environment that allows AI assistants to execute Python code directly against Django projects. Maintains persistent session state between calls, enabling iterative exploration of models, queries, and debugging.

Provides safe shell command execution capabilities for AI agents and tools like VS Code Copilot through a whitelist-based filtering system.

A Node.js MCP server that wraps the Claude Code CLI to enable parallel execution of AI requests for code generation, editing, and refactoring. It features built-in retry logic, model selection, and JSON validation for structured outputs.

MCP server that provides shell script linting via ShellCheck. Allows AI agents to analyze shell scripts for common errors, stylistic issues, and potential bugs.

Interactive shell, scriptable CLI and MCP server for Cloudinary — browse, upload, download, move and delete assets, with a confirm-token preview before anything destructive runs.

Opt-in, token-authenticated MCP server built into the Shelly Android terminal app: read-only tools for terminal output, git status, registered agents and repos on the phone, plus off-by-default run_command and write_file that need an on-device approval tap per call.

A full-featured MCP server for local development with filesystem, shell, editor, session persistence, and security features.

Bridges Claude Code and Claude Chat by exposing session digests as MCP resources and allowing instruction queuing from Chat to Code.

SkillTotal is a local stdio MCP server that lets an agent check a component before installing it. It statically analyzes MCP servers, agent skills, npm/PyPI packages and repos for supply-chain risks, dangerous capabilities (shell, filesystem, network, credentials), prompt-injection surfaces like tool poisoning, and exfiltration paths. Each finding cites file, line and snippet.

A consequence engine for shell commands. Blast Scope scores what a command would actually do before an AI agent runs it.

Lets Claude Code delegate bounded coding tasks to a GLM model as a sub-agent through a single MCP tool that reads, writes, edits, lists directories, and runs shell commands inside a specified project folder. Each run returns only a short report with changed files and token usage, keeping GLM's intermediate tool traffic out of Claude's context.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.

Enables AI agents to start and stop native GNOME Shell screen recordings via MCP tools, returning JSON with file path, size, and duration without depending on ffmpeg or wf-recorder.

Developers: Search your zsh, bash, or fish shell history from Claude Code, Cline, Cursor, Zed, or any MCP client using tools like search_history (full-text with timestamp/CWD/exit code), recent_in_dir, failed_commands, and command_chains for multi-step sequences. Reindex after new activity. Local-only SQLite FTS5 with secrets redacted before storage.

A collection of Model Context Protocol servers that enable Claude Desktop to provide development assistance capabilities with filesystem, Git, shell command, and web search functionality without incurring API usage costs.

Executes Python code snippets safely without shell interpretation, supports parallel batch execution and helper utilities for task decomposition.

Indexes git history, shell commands with exit codes, project docs, and opt-in assistant transcripts into a local SQLite database, then serves ranked, token-budgeted context back over MCP. Uniquely links a failed shell command to the commit that fixed it, so agents can recall what was already tried and what worked.

An MCP server that enables coding agents to execute and manage long-running shell commands asynchronously with capabilities for process monitoring, interaction, and lifecycle management.