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 L2s
MCP & AI Agent Integration

L2s
automation.

16 AI agent actions for L2s — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use L2s to update contacts, move deals through pipelines, and trigger follow-up sequences automatically. Full governance, audit trail, and dry-run safety on every execution.

Connect L2s free Browse all integrations →
No credit card required
Live in production environments
<200ms median execution
Dry-run before production
Execution trace
live
16
actions
100%
governed
<200ms
latency
16
AI agent actions
6
Read operations
10
Write operations
1
High-risk actions (approval gated)
CRM L2s is a CRM integration — use it to automate contact management, deals, and pipeline operations from any AI agent or MCP-compatible runtime.
Actions

What you can do
with L2s.

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 Activity
l2s:get_activity
Fetch a single activity by ID with all details.
Read Low risk
Get Contact
l2s:get_contact
Fetch a single contact by ID with all contact details and custom fields.
Read Low risk
Get Deal
l2s:get_deal
Fetch a single deal by ID with all deal details and associated contacts.
Read Low risk
List Activities
l2s:list_activities
List activities with optional filtering and pagination.
Read Low risk
List Contacts
l2s:list_contacts
List contacts with optional filtering and pagination.
Read Low risk
List Deals
l2s:list_deals
List deals with optional filtering and pagination.
Read Low risk
Add Note
l2s:add_note
Add a note to a contact or deal in L2S CRM.
Write Medium risk
Close Deal
l2s:close_deal
Close a deal as won or lost with optional details.
Write Medium risk
Complete Activity
l2s:complete_activity
Mark an activity as completed with optional notes.
Write Medium risk
Create Activity
l2s:create_activity
Create a new activity in L2S CRM.
Write Medium risk
Create Contact
l2s:create_contact
Create a new contact in L2S CRM.
Write Medium risk
Create Deal
l2s:create_deal
Create a new deal in L2S CRM.
Write Medium risk
Delete Contact
l2s:delete_contact
Delete a contact from L2S CRM. This action cannot be undone.
Write High risk
Send Email
l2s:send_email
Send an email to a contact through L2S email system.
Write Medium risk
Update Contact
l2s:update_contact
Update an existing contact in L2S CRM.
Write Medium risk
Update Deal
l2s:update_deal
Update an existing deal in L2S CRM.
Write Medium risk
MCP & Runtime API

Call L2s
from any AI agent.

Any AI agent — Claude, Cursor, LangChain, AutoGen, or your own — can call L2s actions through the Cerebral OS Runtime API. Governance, credentials, and audit trail fire automatically.

l2s:get_activity READ
# Call via Runtime API
curl
-X POST \
  "https://api.cerebralos.com/v1/runtime/actions/run"
  -H "X-API-Key: YOUR_KEY" \
  -d '{
    "verb": "l2s:get_activity",
    "args": {},
    "execution_id": "agent-001"
  }'
l2s:add_note 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": "l2s:add_note",
    "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 L2s.

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 L2s data
Call l2s:get_activity 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 L2s
Dry-run validates l2s:add_note before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Lead or deal event
Score with AI
Route to right rep
Trigger outreach sequence
How it works

Every L2s action
governed end-to-end.

Cerebral OS isn't a connector. It's the execution layer that sits in front of L2s — 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 L2s action before it touches production. See exactly what would happen before a single real call is made.
Immutable audit trail
Every L2s action is logged — what ran, what changed, who approved it, when it happened. Full history on every verb, forever.
Connect with

L2s works best
alongside these.

Build multi-step workflows that connect L2s to the rest of your stack. All governed. All audited.

Hubspot Salesforce Pipedrive Gmail Slack
L2s integration

Start free.
No credit card required.

Start free with 1,000 runs — no credit card required. Connect L2s in minutes, dry-run every action before it touches production, full audit trail on everything.

Start free — 1,000 runs Browse all integrations →