jotsu-mcp
Verified Safeby getjotsu
Overview
General-purpose library for implementing the Model Context Protocol (MCP) and creating workflows that orchestrate MCP tools, resources, and prompts, particularly for LLM integrations.
Installation
python -m jotsu.mcp.workflowEnvironment Variables
- OPENAI_API_KEY
- ANTHROPIC_API_KEY
- CLOUDFLARE_ACCOUNT_ID
Security Notes
The server uses `asteval` for dynamic execution of Python-like expressions within workflows. While designed to be safer than `eval()` by limiting system access, dynamic code execution still carries inherent risks if workflow definitions are untrusted. Network requests are made to external MCP servers and OAuth endpoints, with URLs defined in workflow configurations or discovered via OAuth metadata. OAuth authentication initiates a local web server and opens a browser, which is a standard pattern for local development. Credentials can be stored locally, with an optional encryption layer using `cryptography`. External API keys are expected via environment variables, not hardcoded. No other obvious malicious patterns or obfuscation were detected.
Similar Servers
fastmcp
An ergonomic interface and framework for building, connecting, and managing Model Context Protocol (MCP) servers and clients, offering features like tool-use, resource access, prompt rendering, authentication, and background task management.
mcp-use
Build full-stack Model Context Protocol (MCP) applications, including AI agents, MCP servers, and clients in both Python and TypeScript, with integrated debugging and UI capabilities.
mcp-context-forge
Retrieves web content and files from any URL, converting them into high-quality markdown format with support for various content types and conversion engines.
mcp-interviewer
A Python CLI tool designed to evaluate, test, and generate reports on Model Context Protocol (MCP) servers to ensure compatibility and quality for LLM agent use cases.