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 Pumble
MCP & AI Agent Integration

Pumble
automation.

17 AI agent actions for Pumble — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Pumble to send alerts, post updates, and coordinate team actions based on triggers. Full governance, audit trail, and dry-run safety on every execution.

Connect Pumble free Browse all integrations →
No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
17
actions
100%
governed
<200ms
latency
17
AI agent actions
8
Read operations
9
Write operations
3
High-risk actions (approval gated)
Communication Pumble is a Communication integration — use it to automate messaging, notifications, and team collaboration from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Pumble.

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 Channel
pumble:get_channel
Fetch details of a specific channel including member count and settings.
Read Low risk
Get Message
pumble:get_message
Fetch a specific message by timestamp from a channel.
Read Low risk
Get User
pumble:get_user
Fetch details of a specific user including profile information and status.
Read Low risk
Get Workspace
pumble:get_workspace
Fetch details of a specific workspace including member count and settings.
Read Low risk
List Channels
pumble:list_channels
List channels in a workspace with optional filtering.
Read Low risk
List Messages
pumble:list_messages
List messages from a channel with optional filtering and pagination.
Read Low risk
List Users
pumble:list_users
List users in a workspace with optional filtering.
Read Low risk
List Workspaces
pumble:list_workspaces
List all workspaces the authenticated user has access to.
Read Low risk
Add Reaction
pumble:add_reaction
Add an emoji reaction to a message.
Write Medium risk
Create Channel
pumble:create_channel
Create a new channel in a workspace.
Write Medium risk
Delete Channel
pumble:delete_channel
Permanently delete a channel and all its messages. This action cannot be undone.
Write High risk
Delete Message
pumble:delete_message
Permanently delete a message. This action cannot be undone.
Write High risk
Invite User
pumble:invite_user
Invite a new user to a workspace via email.
Write Medium risk
Remove Reaction
pumble:remove_reaction
Remove an emoji reaction from a message.
Write High risk
Send Message
pumble:send_message
Send a text message to a channel or thread.
Write Medium risk
Update Channel
pumble:update_channel
Update channel properties like name, description, or archive status.
Write Medium risk
Update Message
pumble:update_message
Update the text content of an existing message.
Write Medium risk
MCP & Runtime API

Call Pumble
from any AI agent.

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

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

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 Pumble data
Call pumble:get_channel 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 Pumble
Dry-run validates pumble:add_reaction before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Message or alert triggered
Route to right channel
Notify relevant team
Log to audit trail
How it works

Every Pumble action
governed end-to-end.

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

Pumble works best
alongside these.

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

Slack Gmail Microsoft Teams Discord Twilio
Pumble integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →