MCP & AI Agent Integration

Discourse
automation.

22 AI agent actions for Discourse — callable from any MCP-compatible runtime, Claude, Cursor, or Cerebral OS workflow. Use Discourse to create tasks, update project status, and coordinate work across teams automatically. 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
22
actions
100%
governed
<200ms
latency
22
AI agent actions
8
Read operations
14
Write operations
2
High-risk actions (approval gated)
Productivity Discourse is a Productivity integration — use it to automate tasks, projects, and team workflows from any AI agent or MCP-compatible runtime.
Actions

What you can do
with Discourse.

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 Category
discourse:get_category
Fetch detailed information about a specific category.
Read Low risk
Get Post
discourse:get_post
Fetch a single post with its content and metadata.
Read Low risk
Get Topic
discourse:get_topic
Fetch a single topic with its posts and metadata.
Read Low risk
Get User
discourse:get_user
Fetch a single user's profile information including stats and preferences.
Read Low risk
List Categories
discourse:list_categories
List all categories available in the Discourse instance.
Read Low risk
List Notifications
discourse:list_notifications
List notifications for the current user or specified user.
Read Low risk
List Topics
discourse:list_topics
List topics with various filtering and sorting options.
Read Low risk
List Users
discourse:list_users
List users with filtering and sorting options.
Read Low risk
Bookmark Post
discourse:bookmark_post
Bookmark a post with optional reminder and note.
Write Medium risk
Create Post
discourse:create_post
Create a new post (reply to existing topic or create new topic).
Write Medium risk
Create Topic
discourse:create_topic
Create a new topic or private message in Discourse.
Write Medium risk
Create User
discourse:create_user
Create a new user account in Discourse.
Write Medium risk
Delete Post
discourse:delete_post
Delete a post. Depending on site settings, this may be reversible.
Write High risk
Delete Topic
discourse:delete_topic
Permanently delete a topic and all its posts. This action cannot be easily undone.
Write High risk
Like Post
discourse:like_post
Like or unlike a post.
Write Low risk
Mark Notifications Read
discourse:mark_notifications_read
Mark notifications as read (specific notification or all notifications).
Write Medium risk
Search
discourse:search
Search for topics, posts, users, and categories across the Discourse instance.
Write Low risk
Send Private Message
discourse:send_private_message
Send a private message to one or more users or groups.
Write Medium risk
Suspend User
discourse:suspend_user
Suspend or unsuspend a user account.
Write Medium risk
Update Post
discourse:update_post
Update an existing post's content.
Write Medium risk
Update Topic
discourse:update_topic
Update an existing topic's properties like title, category, tags, or status.
Write Medium risk
Update User
discourse:update_user
Update an existing user's profile information and settings.
Write Medium risk
MCP & Runtime API

Call Discourse
from any AI agent.

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

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

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 Discourse data
Call discourse:get_category 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 Discourse
Dry-run validates discourse:bookmark_post before execution
Approval gate fires if risk level is high
Action executes with full governance — logged, audited, reversible
Trigger
Task or project event
Update status automatically
Notify assignees
Sync across tools
How it works

Every Discourse action
governed end-to-end.

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

Discourse works best
alongside these.

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

Discourse integration

Start free.
No credit card required.

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

Start free — 1,000 runs Browse all integrations →