Platform
Platform Overview Maps Memory Shadow Mode Widget Governance Actions Integrations
Developers
Overview Catalog Guardrails Dry Run Idempotency Credentials Audit Trail API Reference
Company
About Blog Contact Book a Demo
MCP Integrations Dust
MCP & AI Agent Integration

Dust
automation.

14 AI agent actions for Dust — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Dust to resolve tickets, route conversations, and escalate edge cases without a human in the loop. Full governance, audit trail, and dry-run safety on every execution.

Connect Dust free Browse all integrations →
No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
14
actions
100%
governed
<200ms
latency
14
AI agent actions
9
Read operations
5
Write operations
1
High-risk actions (approval gated)
Customer Support Dust is a Customer Support integration — use it to automate ticket management, conversations, and escalations from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Dust.

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 Assistant
dust:get_assistant
Fetch a single assistant by ID with configuration and capabilities.
Read Low risk
Get Conversation
dust:get_conversation
Fetch a single conversation by ID with messages and metadata.
Read Low risk
Get Data Source
dust:get_data_source
Fetch a single data source by ID with configuration and status.
Read Low risk
Get Run
dust:get_run
Fetch a single run by ID with execution details and status.
Read Low risk
List Assistants
dust:list_assistants
List assistants in a workspace with pagination support.
Read Low risk
List Conversations
dust:list_conversations
List conversations in a workspace with pagination support.
Read Low risk
List Data Sources
dust:list_data_sources
List data sources in a workspace with pagination support.
Read Low risk
List Runs
dust:list_runs
List runs in a workspace with pagination and filtering support.
Read Low risk
Search Data Source
dust:search_data_source
Search for documents within a data source using semantic search.
Read Low risk
Create Conversation
dust:create_conversation
Create a new conversation in a workspace.
Write Medium risk
Create Data Source
dust:create_data_source
Create a new data source in a workspace.
Write Medium risk
Create Run
dust:create_run
Create and execute a new run in a workspace.
Write Medium risk
Delete Data Source
dust:delete_data_source
Delete a data source from a workspace. This action cannot be undone.
Write High risk
Send Message
dust:send_message
Send a message to an existing conversation.
Write Medium risk
MCP & Runtime API

Call Dust
from any AI agent.

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

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

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 Dust data
Call dust:get_assistant 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 Dust
Dry-run validates dust:create_conversation before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Support ticket created
Classify with AI
Auto-resolve or escalate
Notify team with full context
How it works

Every Dust action
governed end-to-end.

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

Dust works best
alongside these.

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

Zendesk Intercom Reamaze Slack Hubspot
Dust integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →