MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
A secure MCP server for executing whitelisted development commands with comprehensive security controls.
npm MIT -
A robust command execution service with daily log rotation, designed to securely manage and execute system commands with safety checks and logging.
MIT -
A secure MCP CLI server implementation with comprehensive path whitelist validation, providing controlled file system operations and command execution in a protected environment. Features include strict security measures, real-time path validation, secure
npm MIT -
Enhanced MCP server for secure shell command execution with context preservation and AI optimization
npm MIT -
MCP server written in rust for secure local code execution
-
ssh-mcpgithub.com/narthanaj/ssh-mcpupdated this year
A secure SSH server for the Model Context Protocol (MCP), enabling LLMs to execute commands on remote hosts
MIT -
Bounded local execution runtime for ChatGPT and MCP on macOS — 20 tools, transactional installs, package provenance, and OpenAI Secure MCP Tunnel.
Apache-2.0 ★ 2 -
MCP Server for secure, sandboxed code execution — run Python, JavaScript, and TypeScript from AI agents safely.
★ 3 -
A secure terminal execution server implementing the Model Context Protocol (MCP). This server provides controlled command execution capabilities with security features and resource limits.
npm MIT -
Model Context Protocol server for secure JavaScript code execution in Deno sandbox
npm MIT -
sandbox-ai-wasmgithub.com/amafjarkasi/sandbox-ai-wasmupdated this year
Secure AI code execution platform powered by Edge.js WASM sandboxing. Run untrusted AI-generated code with sub-5ms cold starts, 60x faster than Docker containers. Features multi-engine support (V8, JSC, QuickJS), MCP agent interface, real-time dashboards, comprehensive security with dangerous code detection, audit logging, and rate limiting.
-
Secure, hardened Model Context Protocol (MCP) server for safe Ubuntu system operations — policy-controlled file access, command execution, package search, and full audit trail with defense-in-depth security.
MIT ★ 1 -
A Model Context Protocol server for secure Docker container execution
pypi MIT -
shell-mcpgithub.com/zatevakhin/shell-mcpupdated this year
A Model Context Protocol (MCP) server that provides secure shell command execution
MIT ★ 2 -
Authorization-first, MCP-governed security execution for explicitly approved environments.
MIT ★ 1 -
shellgategithub.com/maugus2/shellgate-mcp-serverupdated this year
Secure shell execution for AI agents — MCP server + CLI
npm MIT -
@uarlouski/ssh-mcp-servergithub.com/uarlouski/ssh-mcp-serverupdated this year
MCP server enabling AI assistants to securely execute SSH commands, transfer files via SFTP, manage port forwarding, and use parameterized command templates with comprehensive security controls
npm Apache 2.0 -
Secure terminal command execution for Model-Context-Protocol servers
npm MIT -
bentorungithub.com/vladkol/bentorunupdated this year
An MCP server that provides a secure isolated environment for executing Python code.
Apache-2.0 ★ 5 -
nix-execgithub.com/amadejkastelic/nix-execupdated this year
MCP server for secure, sandboxed code execution using Nix Flakes and Bubblewrap
MIT -
Zero-trust security runtime for AI agents with deterministic policy enforcement, guarded execution, approvals, redaction, MCP protection, and tamper-evident auditing.
Apache-2.0 ★ 5 -
code-sandbox-mcpgithub.com/feifeigood/code-sandbox-mcpupdated this year
MCP server for E2B code sandbox - Execute code and commands in secure E2B sandboxes
pypi MIT -
secure-banking-mcpgithub.com/Lawaa/secure-banking-mcpupdated this year
Enterprise-grade FastMCP (Python 3.12) server demonstrating identity-isolated AI tool execution with out-of-band JWT authentication, multi-tenant database guards, and automated Pytest/Allure security testing.
-
Command line interface for MCP clients with secure execution and customizable security policies
MIT ★ 179 -
Zero-trust AI security research engine built on MCP, Tauri v2, and Rust — with prompt injection defense and sandboxed tool execution
MIT ★ 5 -
🛡️ Ephemeral privacy & security middleware for Model Context Protocol (MCP). Zero-persistence credential masking & fail-closed execution guard for AI agents.
MIT -
postgres-mpc-servergithub.com/kaizen403/postgres-mpc-serverupdated this year
Postgres MCP server for AI tooling with secure query execution, observability, and workflow integration.
-
Model Context Protocol (MCP) server for secure sudo command execution with hidden passwords
npm MIT -
Secure AI bridge for Windows PowerShell automation using MCP communication and controlled local execution.
MIT ★ 1 -
A Model Context Protocol server for executing JavaScript in isolated VM contexts with configurable globals and security features
npm MIT -
The in-guest execution agent. Runs security tooling and the MCP bridge inside a Setec microVM. Elastic License 2.0.
NOASSERTION -
Secure MCP server for whitelisted shell command execution with stdin, argv pipelines, timeouts, and structured audit logging.
go MIT ★ 202 -
A secure Model Context Protocol (MCP) server for executing commands in Windows Subsystem for Linux (WSL) with built-in safety features and validation
npm MIT -
Security engine for WordPress AI Abilities — fail-closed risk classification, permission gating, audit logging, and MCP/REST execution controls.
NOASSERTION ★ 2 -
A secure, high-performance Model Context Protocol (MCP) server for SSH command execution and remote file operations
npm MIT -
Static security scanner for machine-learning model files. Checks PyTorch, pickle, joblib, GGUF, SafeTensors, ONNX and Keras checkpoints for code execution before you load them. CLI, GitHub Action, load guard, MCP server.
pypi MIT ★ 2 -
mcp-multilang-sandboxgithub.com/Pit-CL/mcp-multilang-sandboxupdated this year
Multi-language code execution MCP server with Docker isolation. Execute Python, TypeScript, JavaScript, Go, Rust, Bash securely with 0ms container pooling.
-
MCP server for Skully: signed SKILL.md security methodology and executable playbooks for AI agents.
npm MIT -
arx-mcp-servergithub.com/gethammerpath/arx-mcp-serverupdated this year
ARX MCP Server - Execute 100+ security operations with policy enforcement, audit logging, and human approvals
pypi MIT License -
Run code in isolated cloud containers. ConTree gives AI agents secure sandboxed execution environments with full root access, network, and persistent images.
pypi Apache-2.0 ★ 2 -
Security-first reverse-engineering MCP server: untrusted binaries analysed in a no-network bubblewrap chamber, never executed. Isolation proven in CI.
MIT -
Splunk MCP Server – SPL search execution, index/sourcetype discovery, saved searches, and health checks for security investigations
npm Apache-2.0 -
Enterprise Model Context Protocol (MCP) server for secure remote SSH infrastructure orchestration, command execution, and automated SFTP synchronization.
MIT -
shemcpgithub.com/acartine/shemcpupdated this year
Secure shell command execution server for Model Context Protocol (MCP)
npm MIT ★ 2 -
A local security checkpoint for AI agents. MCP firewall, Linux sandbox, secret inspection and auditable tool execution — built in Rust.
MIT ★ 1 -
@tb.p/terminaigithub.com/jhasselbring/terminaiupdated this year
MCP (Model Context Protocol) server for secure SSH remote command execution. Enables AI assistants like Claude, Cursor, and VS Code to execute commands on remote servers via SSH with command validation, history tracking, and web-based configuration UI.
npm MIT -
Secure AI agent execution with MCP, deterministic policies, human approval, idempotency and auditable simulated financial operations.
MIT -
Local-first AI agent orchestrator with MCP server, secure file operations, shell execution, code indexing, and quality gates
npm ISC -
Two-component system bridging Kali Linux penetration testing tools with AI agents via MCP. Flask API server executes 10+ security tools (Nmap, SQLMap, Metasploit, etc.) while MCP client provides seamless AI integration for automated security workflows.
MIT ★ 9 -
code-firewall-mcpgithub.com/egoughnour/code-firewall-mcpupdated this year
A structural similarity-based code security filter for MCP (Model Context Protocol). Blocks dangerous code patterns before they reach execution tools by comparing code structure against a blacklist of known-bad patterns.
pypi MIT -
Hachiman Agent — autonomous security layer for AI agents and MCP. Scan before deployment, authorize before access, monitor during execution, contain when compromised, report everything. Includes an authorized offensive security skill with verified fix-on-fail loops. MIT License. Developer: Nidhish Guhan.
MIT ★ 1 -
corellium-mcpgithub.com/H4RR1SON/corellium-mcpupdated this year
Code-mode Model Context Protocol (MCP) server for Corellium: the full 206-operation mobile-security API behind two tools, executed in a token-isolated V8 sandbox. Ships a token-efficiency A/B evaluator.
MIT ★ 2 -
Secure SSH access for AI agents via MCP. Execute commands across your server fleet with policy enforcement, network controls, and comprehensive audit logging.
Apache-2.0 ★ 30 -
Secure GNU Octave code execution over MCP (FastMCP + FastAPI).
NOASSERTION -
Secure MCP server for WorkBoard OKR and strategy execution platform
AGPL-3.0 ★ 1 -
NIRA REPL MCPgithub.com/pachote/nira-replno update data
Secure code execution sandbox for Claude — run Python, JavaScript, and shell commands
pypi -
Minimal, secure HTTP & SOCKS5 proxy routed through Tor with fail-closed leak protection, non-root execution, and a REST API for circuit rotation and dynamic exit node selection.
oci MIT ★ 7 -
CodeGuardAIgithub.com/Grego-GT/CodeGuardAIupdated this year
CodeGuard AI is an MCP-powered security agent that scans GitHub pull requests for vulnerabilities, uses E2B sandboxes to safely execute live exploits proving these vulnerabilities, and automatically generates secure code fixes with explanations, delivering real-time, actionable security insights to developers and enterprises.
-
A sandboxed, agentic workspace providing secure filesystem, bash, and uv-powered Python execution.
oci ★ 1 -
Security-hardened MCP server for terminal access: deny-by-default policy engine, shell=False sandboxed execution, cwd jail, secret redaction, fail-closed audit log.
MIT