SciAgentKit - Deterministic drug-discovery tools for AI agents
by•
MCP-native scientific tools for reproducible computational biology and AI-driven drug discovery. No hallucinated descriptors, docking scores, or RMSD.
Connect Claude code, Cursor, Gemini cli and Codex to real local tools for molecular analysis, docking, molecular dynamics and reproducible scientific reporting.
Replies
Plug-and-play conda/mamba environments per tool would save a ton of setup headaches, especially for folks juggling RDKit, OpenMM, and AutoDock Vina versions across different projects.
@feyza1156028 Thanks, this is a very good point. Dependency conflicts between RDKit, OpenMM and docking tools are one of the biggest practical problems in these workflows.
We are working toward more isolated and reproducible environments, including tool-specific conda/mamba setups and clearer environment validation before a workflow starts.
Finally something that doesn't make up docking scores out of thin air. Ran a quick Vina job through Claude and the actual numbers came back clean and reproducible, which is rarer than it should be in this space.
@malican69052 Thank you for testing it. That is exactly the problem we wanted to address.
The agent should organise the workflow, but the docking scores must come from the actual scientific engine, together with the parameters and outputs needed to reproduce the run.