mcp-ts-core and mcp-farmer
The TypeScript template (`cyanheads/mcp-ts-core`) and the CLI tool (`boldare/mcp-farmer`) are complements, as the CLI tool is designed to scaffold, test, extend, and analyze MCP servers, which can then be built using the provided TypeScript template.
About mcp-ts-core
cyanheads/mcp-ts-core
TypeScript template for building Model Context Protocol (MCP) servers. Ships with declarative tools/resources, pluggable auth, multi-backend storage, OpenTelemetry observability, and first-class support for both local and edge (Cloudflare Workers) runtimes.
This is a framework for developers to quickly build and deploy specialized AI agent servers that perform specific tasks. It takes declarative definitions of 'tools' and 'resources' (like searching a database or greeting a user) and produces a ready-to-use server, handling common backend complexities like authentication, storage, and logging. Developers who need to create custom, task-specific AI agents without building server infrastructure from scratch would use this.
About mcp-farmer
boldare/mcp-farmer
A CLI tool for scaffolding, testing, extending and analyzing MCP (Model Context Protocol) servers
Provides automated vetting, documentation generation, and AI-assisted tool creation for MCP servers through multiple transport methods (HTTP with Streamable/SSE fallback and stdio). Integrates with popular coding agents (OpenCode, Claude Code, Gemini CLI) via the Agent Client Protocol (ACP) for intelligent tool generation from OpenAPI/GraphQL specs and automated probe testing with LLM-generated inputs. Auto-discovers servers from client configs (Cursor, VS Code, Claude Desktop) and generates shareable HTML/JSON/Markdown audit reports and documentation.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work