"Coze" matching MCP servers:

Enables AI agents to resolve and cross-reference biological entities such as genes, proteins, and aliases across authoritative databases like HGNC, NCBI Entrez, and UniProt, with confidence scores and source citations.

Turns a first-person lab video, a protocols.io protocol or a PDF into an Opentrons Flex or OT-2 protocol that passes Opentrons' simulator. Tools list runs, read the steps, return protocol.py, analyze it and run it on Opentrons' robot-server.

Enables calculation of isolated L-, M-, and S-cone contrast thresholds and mapping them to calibrated 0–100 diagnostic scores for assessing photoreceptor integrity and selective color-vision defects.

Enables deterministic calculation of isolated L-, M-, and S-cone contrast thresholds and conversion into calibrated 0–100 CCT score indices for assessing photoreceptor integrity and selective color-vision defects.

Enables AI agents to translate between Hebrew, English, and Russian with protected values, handle RTL/LTR display and direction analysis, detect code-switched language, transliterate, add or strip nikud, manage terms, and use clinical translation tools via a remote MCP server.

Exposes vaccination-appointment scheduling as standardized MCP tools backed by an in-memory mock backend. Enables agents to list available slots by date and vaccine type, book appointments, check confirmation status, and cancel bookings.

Enables users to train and compare Logistic Regression and KNN models, make breast-cancer predictions, retrieve sample inputs, compute confusion-matrix metrics, generate SHAP explanations, select the best model, and export Parquet audit logs through MCP tools.

A local-first, model-agnostic MCP server that stores personal health data in a SQLite file and provides analysis-ready views for any AI client to log, retrieve, and reason over health records.