Checks MNE-Python and dependency versions (scikit-learn, numpy, scipy, matplotlib) plus runtime directories to confirm the MNE-MCP environment is ready for neurophysiology data analysis.
MIT
520,811 tools. Updated 2026-09-06 09:34
"scikit-learn" matching MCP tools:
- Generate a scikit-learn machine learning pipeline in a project directory. Specify the directory to scaffold a complete ML pipeline structure for immediate use.MIT
- Retrieve crypto education articles from CoinGecko Learn. Filter by category and limit to get structured article cards for research or content.MIT
- Learn separate baseline bands per declared context so normal ranges match each operating regime, avoiding overly wide bands that miss anomalies.MIT
- Retrieve the contiguous run of events in a collection after any position you hold, including edits made in the widget. Use a write ack seq, data_list version, or previous next_since as your mark; omit since to learn the current position.MIT
- Verify AlgoChains Learn Hub is publicly accessible without login by checking HTTP status, RSS MIME type, and subdomain redirect. Read-only health check confirms the learning portal is live.MIT
Matching MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides a standardized interface for interacting with Scikit-learn models and datasets, enabling training, evaluation, and model management through natural language.17MIT
- FlicenseAqualityCmaintenanceMCP server that lets AI assistants access University of Waterloo LEARN course data (announcements, content, grades, assignments, outlines) and search past assessments in Google Drive.10-
Matching MCP Connectors
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
Comments for every page. Search before a task, check a URL's board, post what you learn.
- Learn the essentials of writing WCPS queries: basic syntax, common operations, and best practices for querying rasdaman datacubes.MIT
- Explain a type's fields and its role in methods (construct, mutate, consume, destroy) from graph facts. Learn a struct's shape and handling before reading call sites.AGPL 3.0
- Report agent errors, record solutions, and track failed attempts with a 2-strike protocol to help agents learn from mistakes and avoid recurrence.MIT
- Get the game rules, mechanics, and strategy tips to learn how to play Lucille Protocol.MIT
- Retrieve the structure of a Fluig dataset, including columns and data types, without executing the dataset. This helps understand the schema before building a query.MIT
- Get the current Molpha verification surface to learn where a signed result can be verified. Includes registry version, node set, gateway endpoints, supported chains, and spend caps.MIT
- List available bots, indicators, and exchanges. Get bot details, sections, and indicator defaults for strategies.MIT
- Manage structural blueprints extracted from real documents. Learn from DOCX or PDF, list stored blueprints, delete by name, and use to validate paragraph structure when creating documents.MIT
- Access detailed guides for trust-building areas or interaction form recipes. Find step-by-step instructions on verification, claims, recording, and more.Apache 2.0
- Create a product experiment to track Build-Measure-Learn stages, including title, metric, target, and hypothesis. Manage experiments from idea to learning.MIT
- Maps Hermes /goal, verification evidence, /learn, /journey, and background subagents into Marrow proof and outcome workflows. Provides integration guidance for applying Marrow governance to Hermes agents.MIT
- Summarize a local DBC file to learn its size and node names, providing an overview for initial inspection.MIT
- Extracts conversational style signals from a user message to learn personal habits like catchphrases, emoji use, and tone, without storing private memories.MIT
- Fetch a free sample Brazilian company profile to preview the response format before purchasing paid data retrieval tools through the Brazilayer MCP Server.MIT
- Learn a conservative normal operating range for a tag from historical samples, using robust percentiles, to establish a baseline for anomaly detection. Refuses on insufficient data.MIT