mcp-execution
Verified Safeby bug-ops
Overview
Generates executable, type-safe TypeScript tools from any MCP server, enabling AI agents to progressively load only the tools they need for significant token savings.
Installation
mcp-executionSecurity Notes
The project adheres to Microsoft Rust Guidelines, explicitly denying `unsafe` code. It implements defense-in-depth security measures for command execution, path validation (preventing directory traversal), and limits on file sizes and counts (DoS protection) when scanning user-provided directories. The `mcp-execution-cli` and `runtime/mcp-bridge.ts` validate inputs and sanitize command arguments passed to external MCP servers. Environment variables for sensitive tokens are expected to be passed securely to target servers, not directly handled by the `mcp-execution` server itself. The overall design principle 'No Code Execution' for generated TypeScript (it's for type info) enhances safety. No hardcoded secrets were found. However, the runtime bridge `mcp-bridge.ts` spawns `ChildProcess` which inherently carries some risk if not rigorously validated, though the core Rust components do extensive validation before passing arguments.
Similar Servers
ncp
NCP acts as a universal adapter and orchestrator for Model Context Protocol (MCP) servers and tools. It provides a unified interface for discovery, execution, and management of diverse tools (local CLI, HTTP APIs, internal plugins/Photons, AI skills) through natural language and structured code interaction, enabling AI agents to interact with the broader digital ecosystem.
mcp-typescript-template
This project provides a foundational TypeScript template for developing remote Model Context Protocol (MCP) servers with robust tooling and best practices.
mcp
An MCP server providing a set of mathematical tools (calculator functions) for remote execution via the Model Context Protocol.
photon
A multi-tenant platform that hosts and executes custom Photon MCPs (Model Context Protocol), managing user authentication, sessions, and OAuth 2.1 integrations for dynamic AI applications.