Rockfish MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MANTA_API_URL | No | Manta API URL (required for Manta tools) | |
| ROCKFISH_API_KEY | Yes | Your Rockfish API key | |
| ROCKFISH_API_URL | No | Rockfish API base URL | https://api.rockfish.ai |
| ROCKFISH_PROJECT_ID | No | Project ID for Rockfish | |
| ROCKFISH_ORGANIZATION_ID | No | Organization ID for Rockfish |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_databasesA | List all databases |
| create_databaseC | Create a new database |
| get_databaseB | Get a specific database by ID |
| update_databaseD | Update a database |
| delete_databaseC | Delete a database |
| list_worker_setsC | List all worker sets |
| create_worker_setC | Create a new worker set |
| get_worker_setB | Get a specific worker set by ID |
| delete_worker_setC | Delete a worker set |
| get_worker_set_actionsC | List the actions for a worker-set |
| list_worker_groupsC | List all worker groups |
| list_available_actionsB | List actions (or workers) from all worker-sets |
| list_workflowsB | List all workflows |
| create_workflowC | Create and run a new workflow |
| get_workflowB | Get a specific workflow by ID |
| update_workflowC | Update a workflow |
| list_modelsB | List all models |
| upload_modelC | Upload a new model |
| get_modelC | Get a specific model by ID |
| delete_modelC | Delete a model |
| get_active_organizationC | Get active organization |
| list_organizationsB | List all organizations |
| get_active_projectC | Get active project |
| list_projectsB | List all projects |
| create_projectB | Create a new project |
| get_projectB | Get a specific project by ID |
| update_projectC | Update a project |
| list_datasetsB | List all datasets |
| create_datasetC | Create a new dataset |
| get_datasetC | Get a specific dataset by ID |
| update_datasetC | Update a dataset |
| delete_datasetC | Delete a dataset |
| get_dataset_schemaC | Get the schema for a dataset |
| get_dataset_query_bookmarksB | Retrieve the query bookmarks for a dataset |
| execute_sql_queryC | Execute a SQL query against Rockfish datasets and return results in CSV format |
| obtain_train_configA | Generate training configuration for synthetic data models. Returns a cached train_config_id for use in start_training_workflow. Supports TabGAN (rf_tab_gan) and TimeGAN (rf_time_gan). |
| start_training_workflowA | Build and start a training workflow using a cached config. Automatically detects model type from train_config structure. Use this after obtaining train_config_id from obtain_train_config. |
| update_train_configC | Update training configuration. Modify model hyperparameters (epochs, batch_size, etc.) and/or encoder field classifications (categorical, continuous, ignore). See https://docs.rockfish.ai/model-train.html for config structure. |
| get_workflow_logsA | Stream logs from a workflow execution with configurable log level and collection timeout. Collects logs for specified duration (default 10s), useful for monitoring workflow progress and debugging. Call repeatedly to continue collecting logs from running workflows. |
| get_trained_model_idA | Extract the trained model ID from a completed training workflow. Only works on COMPLETED or FINALIZED workflows. |
| start_generation_workflowC | Start a workflow to generate synthetic data from a trained TabGAN model. |
| obtain_synthetic_dataset_idA | Extract the synthetic dataset ID from a completed generation workflow. Only works on COMPLETED or FINALIZED workflows. |
| plot_distributionA | Generate distribution plot comparing datasets for a specific column. Returns base64-encoded PNG image. Automatically chooses bar plot (categorical) or KDE plot (numerical). |
| get_marginal_distribution_scoreB | Calculate marginal distribution score between two datasets (real vs synthetic). Lower score means more similar distributions. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 44 tools
Most tools target a distinct resource and action (e.g., create_dataset, get_workflow, start_training_workflow). A few listing tools overlap in scope, such as list_available_actions versus get_worker_set_actions, and list_worker_groups versus list_worker_sets, but descriptions generally clarify the differences.
Nearly all tools follow a consistent snake_case verb_noun pattern. Minor deviations include using obtain instead of get for extraction tools and upload_model instead of create_model, but the overall convention remains predictable.
With 44 tools, the surface is heavy for the apparent synthetic-data platform scope. While the domain is broad, many operations could likely be consolidated or grouped, and 25+ tools is generally too many for an agent to navigate efficiently.
Core synthetic data lifecycle is well covered: dataset CRUD, SQL query, model upload, training config, training workflow, generation workflow, and evaluation plots. Minor gaps exist, such as missing delete_project, delete_workflow, and update_model, but agents can work around these.