Molecare MCP server

Read from the package source without running it. The installed server may list more.

• check_server_health

  Check if the molecare-server application is responding on an EC2 instance by hitting its health endpoint.

• clear_cache

  Clear the MCP server's internal cache. Use when you need fresh data after known changes.

• compare_model_runs

  Compare metrics between multiple MLflow runs to evaluate model performance.

• get_all_apps_status

  Get status of all MoleCare applications (web, mobile API, iOS app, Android app) in one call.

• get_app_errors

  Get recent application errors including error messages, endpoints, status codes, and occurrence counts.

• get_app_metrics

  Get application metrics including request counts, error rates, response times, and active users.

• get_app_status

  Get status of all MoleCare applications including web app, mobile API, backend, and ML serving. Use this to check overall system health.

• get_app_store_status

  Get iOS App Store and Android Play Store status including ratings, reviews, and current live versions.

• get_app_versions

  Get deployed versions of all MoleCare applications across environments (production, staging).

• get_backup_history

  Get database backup history including automated and manual backups with their status and sizes.

• get_connection_pools

  Get connection pool status for all database clients showing active, idle, and waiting connections.

• get_database_metrics

  Get database performance metrics including query stats, storage usage, cache hit ratios, and deadlocks.

• get_database_status

  Get status of all databases including PostgreSQL and Redis instances with connection pools and latency.

• get_deployment_status

  Get current deployment status for staging and production environments.

• get_deployments

  Get status of Kubernetes deployments across namespaces. Shows replica counts, images, and health status.

• get_ec2_health

  Get AWS health check status for EC2 instances including instance and system status checks.

• get_ec2_instance

  Get detailed information about a specific EC2 instance by its instance ID.

• get_ec2_instances

  Get all MoleCare EC2 instances with their current state, IP addresses, and instance types. Use this to see all running servers.

• get_ec2_metrics

  Get CloudWatch metrics (CPU, network) for an EC2 instance over a specified time period.

• get_feature_freshness

  Get freshness status of all feature views showing last materialization time and staleness.

• get_feature_store_stats

  Get overall statistics about the Feast feature store including counts and store types.

• get_feature_view_details

  Get detailed information about a specific feature view.

• get_feature_views

  List all Feast feature views with their entities, features, and data sources.

• get_kubernetes_status

  Get Kubernetes cluster status including nodes, namespaces, deployments, and pod health.

• get_mlflow_experiments

  List all MLflow experiments with their status and last update time.

• get_mlflow_runs

  Get MLflow runs for an experiment with metrics, parameters, and status.

• get_mobile_api_status

  Get the current status of the MoleCare mobile API backend including health, version, and response time.

• get_model_version

  Get details of a specific model version including stage, metrics, and run info.

• get_online_features

  Retrieve online features for an entity from Feast feature store.

• get_pipeline_runs

  Get recent CI/CD pipeline runs from GitHub Actions. Shows build status, duration, and triggered by.

• get_pipeline_summary

  Get summary statistics for CI/CD pipelines including success rate, average duration, and failure count.

• get_registered_models

  List all registered ML models in MLflow model registry with versions and stages.

• get_releases

  Get recent releases with version info, release notes, and assets.

• get_service_health

  Get health status of all backend services including databases, cache, storage, auth, and external dependencies.

• get_slow_queries

  Get slow database queries that may need optimization, sorted by total execution time.

• get_system_health

  Get comprehensive health status of all MCP backend services. Use this to check if services are available before making other calls.

• get_table_stats

  Get statistics for database tables including row counts, sizes, and vacuum/analyze status.

• get_training_runs

  Get Metaflow ML training pipeline runs. Shows training status, parameters, and duration.

• get_web_app_status

  Get the current status of the MoleCare web application including health, version, response time, and uptime.

• Code scan59 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitystatic API keys via environment variables6/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

Molecare: common questions

Is Molecare MCP server safe?

Yes, by our scan: it is graded A (85/100). Read the Molecare safety report

How do I install Molecare?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Molecare need an API key?

Yes. The registry entry asks for MOLECARE_API_KEY.

Is Molecare maintained?

The last commit was 2 days ago (2026-09-19). The latest release is v1.1.0.