MCP & AI Agent Integration

Bigml
automation.

20 AI agent actions for Bigml — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Bigml to automate business processes and connect tools in your stack. Full governance, audit trail, and dry-run safety on every execution.

No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
20
actions
100%
governed
<200ms
latency
20
AI agent actions
10
Read operations
10
Write operations
5
High-risk actions (approval gated)
Business Tools Bigml is a Business Tools integration — use it to automate business operations and workflow automation from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Bigml.

Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.

Get Dataset
bigml:get_dataset
Fetch a single dataset by ID with field information and statistics.
Read Low risk
Get Evaluation
bigml:get_evaluation
Fetch a single evaluation by ID with performance metrics and results.
Read Low risk
Get Model
bigml:get_model
Fetch a single model by ID with training information and performance metrics.
Read Low risk
Get Prediction
bigml:get_prediction
Fetch a single prediction by ID with result and confidence information.
Read Low risk
Get Source
bigml:get_source
Fetch a single data source by ID with upload status and field information.
Read Low risk
List Datasets
bigml:list_datasets
List datasets with optional filtering and pagination.
Read Low risk
List Evaluations
bigml:list_evaluations
List evaluations with optional filtering and pagination.
Read Low risk
List Models
bigml:list_models
List models with optional filtering and pagination.
Read Low risk
List Predictions
bigml:list_predictions
List predictions with optional filtering and pagination.
Read Low risk
List Sources
bigml:list_sources
List data sources with optional filtering and pagination.
Read Low risk
Create Dataset
bigml:create_dataset
Create a new dataset from an existing source.
Write Medium risk
Create Evaluation
bigml:create_evaluation
Create an evaluation to measure model performance on a test dataset.
Write Medium risk
Create Model
bigml:create_model
Create a new machine learning model from an existing dataset.
Write Medium risk
Create Prediction
bigml:create_prediction
Create a prediction using a trained model with input data.
Write Medium risk
Create Source
bigml:create_source
Create a new data source from a remote URL.
Write Medium risk
Delete Dataset
bigml:delete_dataset
Permanently delete a dataset and all its dependent resources.
Write High risk
Delete Evaluation
bigml:delete_evaluation
Permanently delete an evaluation.
Write High risk
Delete Model
bigml:delete_model
Permanently delete a model and all its dependent resources.
Write High risk
Delete Prediction
bigml:delete_prediction
Permanently delete a prediction.
Write High risk
Delete Source
bigml:delete_source
Permanently delete a data source and all its dependent resources.
Write High risk
MCP & Runtime API

Call Bigml
from any AI agent.

Any AI agent — Claude, Cursor, LangChain, AutoGen, or your own — can call Bigml actions through the Cerebral OS Runtime API. Governance, credentials, and audit trail fire automatically.

bigml:get_dataset READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "bigml:get_dataset",
    "args": {},
    "execution_id": "agent-001"
  }'
bigml:create_dataset WRITE
# Dry-run first — no production risk
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "bigml:create_dataset",
    "args": {},
    "execution_id": "agent-001",
    "metadata": {"dryRun": true}
  }'
Get your Runtime API key at app.cerebralos.com/signup — 1,000 free executions, no credit card required.
AI agent examples

What your AI agent
can do with Bigml.

Real patterns your AI agent can execute via MCP or the Runtime API. Every action governed, dry-run safe, and fully audited.

Trigger
AI agent needs Bigml data
Call bigml:get_dataset via MCP or Runtime API
AI processes result and takes next action
Full execution logged to audit trail automatically
Trigger
Workflow needs to write to Bigml
Dry-run validates bigml:create_dataset before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Bigml
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Bigml action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Bigml — adding governance, dry-run safety, and a full audit trail to every operation.

Governance first
Every verb carries a risk classification. High-risk writes require explicit approval gates before they execute in production.
Dry-run safe
Simulate any Bigml action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Bigml action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Bigml works best
alongside these.

Build multi-step workflows that connect Bigml to the rest of your stack. All governed. All audited.

Bigml integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect Bigml in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →