MCP & AI Agent Integration

Faraday
automation.

20 AI agent actions for Faraday — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Faraday 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
11
Read operations
9
Write operations
1
High-risk actions (approval gated)
Business Tools Faraday 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 Faraday.

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 Cohort
faraday:get_cohort
Fetch a single cohort by ID with definition and statistics.
Read Low risk
Get Dataset
faraday:get_dataset
Fetch a single dataset by ID with schema and status information.
Read Low risk
Get Outcome
faraday:get_outcome
Fetch a single outcome by ID with definition and statistics.
Read Low risk
Get Prediction
faraday:get_prediction
Fetch a single prediction by ID with model details and performance metrics.
Read Low risk
Get Prediction Results
faraday:get_prediction_results
Get prediction results for a completed prediction model.
Read Low risk
Get Target
faraday:get_target
Fetch a single target by ID with configuration and deployment status.
Read Low risk
List Cohorts
faraday:list_cohorts
List cohorts with optional filtering and pagination.
Read Low risk
List Datasets
faraday:list_datasets
List datasets with optional filtering and pagination.
Read Low risk
List Outcomes
faraday:list_outcomes
List outcomes with optional filtering and pagination.
Read Low risk
List Predictions
faraday:list_predictions
List predictions with optional filtering and pagination.
Read Low risk
List Targets
faraday:list_targets
List targets with optional filtering and pagination.
Read Low risk
Create Cohort
faraday:create_cohort
Create a new cohort based on dataset filters.
Write Medium risk
Create Dataset
faraday:create_dataset
Create a new dataset in Faraday.
Write Medium risk
Create Outcome
faraday:create_outcome
Create a new outcome definition for tracking business events.
Write Medium risk
Create Prediction
faraday:create_prediction
Create a new prediction model and start training.
Write Medium risk
Create Target
faraday:create_target
Create a new target to deploy predictions to external platforms.
Write Medium risk
Delete Dataset
faraday:delete_dataset
Permanently delete a dataset and all its data.
Write High risk
Deploy Target
faraday:deploy_target
Deploy a target to start sending data to the external platform.
Write Medium risk
Pause Target
faraday:pause_target
Pause an active target to stop sending data to the external platform.
Write Medium risk
Update Dataset
faraday:update_dataset
Update an existing dataset's metadata and configuration.
Write Medium risk
MCP & Runtime API

Call Faraday
from any AI agent.

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

faraday:get_cohort READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "faraday:get_cohort",
    "args": {},
    "execution_id": "agent-001"
  }'
faraday:create_cohort 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": "faraday:create_cohort",
    "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 Faraday.

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 Faraday data
Call faraday:get_cohort 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 Faraday
Dry-run validates faraday:create_cohort before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Event in Faraday
Process with AI agent
Take governed action
Log to audit trail
How it works

Every Faraday action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of Faraday — 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 Faraday action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every Faraday action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

Faraday works best
alongside these.

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

Faraday integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →