Ask your agent in plain language. Each of these maps to a real tool on the server.
create_source
Create a new data source in BigML from a remote URL. The source is the first step in the ML pipeline — raw data is imported and parsed for further processing into datasets. Supports CSV files, JSON, Excel files, and other formats accessible via URL.
create_batch_prediction
Create a batch prediction to generate predictions for an entire dataset at once. More efficient than individual predictions when processing large volumes of data. The batch prediction runs asynchronously; check its status to know when results are ready.
update_resource
Update a BigML resource's mutable attributes. BigML resources are mostly immutable — only metadata fields like name, description, tags, and category can be updated after creation.
list_resources
List BigML resources of a given type with filtering, ordering, and pagination. Returns a paginated list of resources along with metadata about the total count and navigation. Use filters to narrow results by name, tags, creation date, and other resource-specific fields.
create_cluster
Create an unsupervised cluster model to group data instances by similarity. Computes centroids representing the center of each cluster. After creation, use predictions to assign new data points to the nearest cluster centroid.
manage_project
Create or update a BigML project. Projects organize resources into logical groups. Resources can be assigned to a project during creation, and all child resources inherit the project from their parent source.
create_dataset
Create a new dataset in BigML from a source, another dataset, or a list of datasets. Datasets are processed, structured representations of data with statistical summaries for each field. Supports sampling, filtering, field selection, and train/test splitting.
delete_resource
Permanently delete a BigML resource. This action is irreversible. Deleting a project will also delete all resources within that project.
execute_whizzml
Execute a WhizzML script on BigML's servers. WhizzML is a domain-specific language for automating ML workflows. Provide either an existing script ID or inline source code to execute. Executions run asynchronously — check the execution status and retrieve results when finished.
get_resource
Retrieve detailed information about a specific BigML resource by its ID. Returns the full resource object including status, fields, configuration, and results. Useful for checking the status of asynchronous operations (source creation, model training, evaluations, etc.) and retrieving model metrics.
train_model
Train a machine learning model from a dataset. Supports multiple model types: decision tree, ensemble (random forest, boosted trees), deepnet (neural network), logistic regression, linear regression, and time series. Choose the model type based on your task — classification, regression, forecasting, etc.
create_evaluation
Evaluate a supervised model's performance by comparing its predictions against a test dataset. Returns metrics like accuracy, precision, recall, and F-measure for classification tasks, or MSE and R-squared for regression tasks. Works with decision trees, ensembles, deepnets, logistic regressions, linear regressions, and time series models.
create_prediction
Generate a prediction from a trained supervised model. Supports predictions from decision trees, ensembles, deepnets, logistic regressions, linear regressions, and fusions. Provide input data as field-value pairs. Returns the predicted outcome along with confidence/probability information.
create_anomaly_detector
Create an anomaly detector using isolation forest algorithms. Identifies unusual data points in a dataset by measuring how easily they can be isolated from the rest of the data. After creation, use anomaly score predictions to evaluate how anomalous new data points are.
create_optiml
Create an OptiML for automated model selection and hyperparameter optimization. BigML will automatically create and evaluate hundreds of models with different algorithms and configurations to find the best performing model for your dataset. Supports classification and regression tasks.
download_batch_prediction
Download the CSV output of a finished BigML batch prediction. Check processing status with get_resource first.
create_anomaly_score
Score a new data instance with a trained BigML anomaly detector. Scores closer to 1 indicate more anomalous instances.
get_account_status
Retrieve BigML account status, including the task and subscription information returned for the connected account or organization.
create_inline_source
Import CSV text or a JSON string directly as a new BigML source. Use create_dataset after the source finishes processing.
train_unsupervised_model
Train an association discovery model, topic model, or principal component analysis model from a dataset. Use get_resource to retrieve learned rules, topics, or components when processing finishes.
create_forecast
Forecast future values from a trained BigML time series. Supply a positive horizon per objective field ID. Retrieve the resource to inspect forecasts and confidence intervals.
create_centroid
Assign a new data instance to the nearest centroid in a trained BigML cluster. The complete result includes centroid_id, centroid_name, and distance when available.
Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.
{"mcpServers": {"metorial": {"url": "<your-magic-mcp-url>"}}}
claude mcp add --transport http metorial <your-magic-mcp-url>
codex mcp add metorial --url <your-magic-mcp-url>codex mcp login metorial
One governed layer for every app your agents reach, not a separate connector per tool.
Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.
Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.
Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.
Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.
Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.
Upload, download, create, copy, move, rename, trash, and permanently delete files and folders in Google Drive. Search for files using complex queries filtering by name, MIME type, owner, modification date, labels, and other metadata. Share files and folders with specific users, groups, or domains with role-based permissions (owner, writer, commenter, reader). Manage shared drives and their members. Export Google Workspace files (Docs, Sheets, Slides) to standard formats like PDF, DOCX, and XLSX. Track file revision history and restore earlier versions. Create, read, update, and delete threaded comments and replies on files. Read label definitions and search files by label. Browse the Drive apps installed for your account. Store app-specific data in a hidden per-user folder.
Build, manage, and deploy machine learning models via BigML's cloud platform. Create data sources from files, URLs, or external databases. Process datasets with transformations, sampling, filtering, and aggregation. Train supervised models (decision trees, ensembles, deepnets, logistic/linear regressions, time series) and unsupervised models (clusters, anomaly detectors, topic models, associations, PCA). Generate single or batch predictions including classifications, regressions, forecasts, anomaly scores, and centroids. Evaluate model performance with accuracy and precision metrics. Automate model selection with OptiML. Combine heterogeneous models using fusions. Script and automate ML workflows with WhizzML. Export models for local use. Manage organizations, projects, and external database connectors.
Common questions about connecting Bigml to AI agents with Metorial.
