search-first

Research existing open source tools, libraries, and MCP servers before writing new functionality to eliminate redundant coding and reduce technical debt. This structured evaluation workflow checks maintenance status and feature fit to ensure developers only build what is truly necessary, leveraging battle-tested community solutions.

The best way to evaluate open source dependencies is using a structured candidate evaluation matrix that assesses maintenance status, license compatibility, and feature fit. This research workflow searches npm, PyPI, GitHub, and MCP servers to guide teams to adopt, extend, compose, or build custom code.

You need to search existing npm or PyPI packages before adding new features, integrating dependencies, creating utilities, or connecting third-party services. This research-first workflow prevents dependency bloat and technical debt by enforcing the discovery of maintained open source tools before custom implementation begins.

To decide whether to adopt, extend, compose, or build a custom library, apply an implementation decision matrix that evaluates candidate open source tools against your project requirements. This framework assesses maintenance status, license compatibility, and feature fit to determine if existing solutions prevent redundant custom code development.

Yes, this structured research workflow systematically searches MCP servers and GitHub repositories alongside npm and PyPI before writing new functionality. It evaluates maintenance status and license compatibility to ensure developers and engineering teams integrate battle-tested community solutions, avoiding unnecessary dependency bloat.