mokei
by TairuFramework
Overview
Mokei is a TypeScript toolkit for creating, interacting with, and monitoring clients and servers using the Model Context Protocol (MCP), facilitating AI model integration and tool execution. The 'fetch' MCP server specifically provides a tool to fetch URLs and convert their content to markdown.
Installation
pnpm build && node --experimental-vm-modules mcp-servers/fetch/lib/index.jsEnvironment Variables
- OPENAI_API_KEY
Security Notes
The '@mokei/mcp-sqlite' server is highly vulnerable to SQL injection if SQL strings are generated by an LLM without strict sanitization, as it directly executes user-provided SQL. The '@mokei/mcp-fetch' server can be susceptible to Server-Side Request Forgery (SSRF) if it processes untrusted URLs. The 'ContextHost' and 'ProxyHost' components execute arbitrary commands via `nano-spawn`, requiring careful control over the 'command' and 'args' provided to prevent remote code execution, making the framework's security highly dependent on secure configuration and input validation at the application level.
Similar Servers
mcp-use
A full-stack framework for building Model Context Protocol (MCP) servers, MCP clients, and AI agents in both Python and TypeScript, supporting interactive UI widgets and robust debugging.
mcp-openapi-server
Exposes OpenAPI endpoints as Model Context Protocol (MCP) tools, enabling Large Language Models (LLMs) to discover and interact with REST APIs through a standardized protocol.
boilerplate-mcp-server
This boilerplate provides a production-ready foundation for developing custom Model Context Protocol (MCP) servers in TypeScript to connect AI assistants with external APIs and data sources, exemplified by an IP geolocation lookup tool.
mcp
A TypeScript SDK for building and interacting with Model Context Protocol (MCP) servers, facilitating AI agent interaction through exposed tools, prompts, and resources via JSON-RPC over HTTP/SSE.