"Learning or Writing Code in Python" matching MCP servers:

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.

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 training, evaluating, and comparing Logistic Regression and KNN models on the Wisconsin breast cancer dataset, then predicting malignant or benign diagnoses from patient feature inputs and generating SHAP explanations for the selected model. Every tool call is logged to a Parquet audit trail that can be exported for review.

Enables training and comparing Logistic Regression and KNN models, retrieving sample patient inputs, predicting malignant or benign cases, evaluating metrics, selecting the best model, generating SHAP explanations, and exporting a Parquet audit log through MCP tools.

Enables training and comparing Logistic Regression and KNN models, generating predictions and SHAP explanations, selecting the best model, and exporting Parquet audit logs through MCP tools.

Enables users to train and compare breast-cancer classification models, obtain sample inputs, make predictions with Logistic Regression or KNN, evaluate metrics, select the best model, generate SHAP explanations, and export Parquet audit logs through MCP tools.

Enables training, predicting, evaluating, and explaining Logistic Regression and KNN models for breast cancer classification through MCP tools. It also supports model selection, SHAP explanations, and Parquet audit exports.

Enables users to train and evaluate Logistic Regression and KNN models for breast cancer diagnosis, generate predictions and SHAP explanations, select the best-performing model, and export Parquet audit logs through MCP tools.

Enables users to train, evaluate, and compare Logistic Regression and KNN breast-cancer models, generate predictions and SHAP explanations, select the best model, and export Parquet audit logs through MCP tools.

Enables training, evaluating, selecting, and explaining breast cancer prediction models through MCP tools for predictions, metrics, SHAP explanations, sample inputs, and Parquet audit exports.

Enables training and comparing Logistic Regression and KNN models, generating sample patient inputs, making malignant/benign predictions, evaluating confusion-matrix metrics, selecting the best model, producing SHAP explanations, and exporting Parquet audit logs through MCP tools.

Enables training and comparing logistic regression and KNN models, generating predictions and SHAP explanations, selecting a best model, and exporting Parquet audit logs through MCP tools.

Exposes MCP tools that train, evaluate, compare and explain Logistic Regression and KNN models on the Wisconsin breast cancer dataset, then serve malignant/benign predictions with SHAP explanations and a Parquet audit log of every call. It also provides ready-to-use sample patient inputs and model-selection tooling so agents can run a full ML workflow through natural language.

Enables training and comparing logistic regression and KNN models, retrieving sample patient inputs, generating predictions and confusion-matrix metrics, selecting the best model, producing SHAP explanations, and exporting Parquet audit logs through MCP tools.

Enables training and comparing Logistic Regression and KNN models, making breast-cancer predictions, evaluating confusion-matrix metrics, selecting the best model, generating SHAP explanations, and exporting a Parquet audit log through MCP tools.

Enables users to train and compare logistic regression and KNN breast-cancer models, get predictions, review confusion-matrix metrics, select the best model, generate SHAP explanations, and export Parquet audit logs through MCP tools.

Enables users to train and compare Logistic Regression and KNN models on the Wisconsin breast cancer dataset, run predictions on patient feature inputs, compute confusion-matrix metrics and select the best model by malignant recall, generate global and local SHAP explanations, and export Parquet audit logs of every tool call. Also provides sample test-set inputs so agents can invoke prediction tools with valid 30-feature payloads.

An MCP server for querying the KEGG bioinformatics database, providing tools, resource templates, and guided prompts for pathways, genes, compounds, and more.

Enables users to compare U.S. online telehealth programs by specialty, treatment, state, and budget, with sourced pricing, fees, lab requirements, and LegitScript status.

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.

An MCP server that grounds protein research in the UniProt SPARQL endpoint, providing tools for querying proteins, sequences, variants, diseases, and more via intent-named tools and raw SPARQL.

Explains why two scientific papers disagree. A contradiction explorer for bench scientists that compares two studies' designs and grounds every claim in a verbatim quote from the source text.

Grounds gene-nomenclature work in the HUGO Gene Nomenclature Committee (HGNC) dataset, enabling resolution of gene symbols and IDs to canonical HGNC identifiers, plus cross-references and batch operations.

An MCP server implementing the ROBINS-I V2 framework for risk-of-bias assessment in non-randomized studies, with deterministic algorithms and full provenance. It enables users to parse study documents, specify target trial results, answer signalling questions with evidence-bound quotes, and compute or override domain judgements.

MyChart MCP Server

Enables scoring the WHO-5 Well-Being Index from five answers, returning a 0–100 score and a low, reduced, or normal band without providing a diagnosis.

Verified ICD-10-CM code lookup & validation for AI agents — official descriptions, not guesses.

TransBench is a translational research agent that takes free-text clinical observations, decomposes them into biological axes, generates falsifiable hypotheses grounded in PubMed evidence, and designs reproducible computational experiments with concrete datasets for Claude Science.

Monitors PubMed and medRxiv for configurable research topics, summarizes papers using a local LLM, and stores deduplicated results in a local database.

Enables natural language querying of brain volumes (NIfTI) with a fixed set of tools, returning visualizations and reproducible nilearn code.

Enables Claude Desktop to query and analyze diabetes data from Omnipod 5 and Glooko through natural language, providing clinical audit and triage insights such as time in range, trends, and bolus analysis.

MCP server for automated ICD-10 medical coding. Code clinical text to ICD-10-CM diagnoses, search 74,000+ codes, and de-identify PHI via the AutoICD API.

MCP server exposing REINVENT4 generative molecular-design operations as validated, LLM-callable tools for drug discovery, including sampling, transfer learning, reinforcement learning, and molecular analysis.

Enables AI agents to search a directory of Iranian doctors by full or partial name, city or province, and specialty, and returns the best match with alternatives plus clinic addresses, phones, weekly hours, and map links. It is read-only and requires no authentication, so it cannot book appointments or provide medical advice.

Provides read-only tools for planning, writing, and auditing lesion network mapping and connectome-based localization papers, including design classification, methods checklists, phrasebooks, limitations, and manuscript auditing.

Enables developers to diagnose why FSE 2.0 CDA2 documents are rejected by validating locally, explaining schematron/XSD errors, looking up code systems, and generating synthetic sample documents.

Renders interactive 2D molecular structure diagrams from SMILES notation and computes molecular properties like molecular weight, LogP, and TPSA, directly in the chat.

Search 200M+ patents and scientific literature in natural language using PatSnap's global R&D intelligence database.

Enables AI assistants to answer healthcare REIT portfolio questions with deterministic, provable answers grounded in Omega Healthcare 10-K filings and CMS nursing home data, including status, caveats, and provenance.

Enables a dental office's AI agent to verify benefits for a batch of up to 25 patients in a single MCP call, returning coverage percentages, frequency limits, waiting periods and deductible/annual-maximum remaining, each tied to a plan-clause citation. Exceptions such as identity mismatches or ambiguous cases are routed to a human review queue rather than guessed, with every call audit-logged.