Ordinal connector for AI agents

Tools your social media agent reaches for on Ordinal, scoped per user.

CALL ANY TOOL

56 tools for social media in Ordinal: create, schedule, and archive posts, manage ideas and labels, request approvals, plan engagements, and read LinkedIn and X analytics.

ordinal_approval_delete

Delete approval

Delete an approval request by id. Returns deletedApproval with its id, status, isBlocking, message, dueDate, approvedAt, user and requestedBy. Use ordinal_post_approvals_list to find the approval id.

Parameters

Name

Type

Required

Description

approval_id

string

Required

ID of the approval to delete (UUID).

ordinal_approvals_create

Create approvals

ordinal_approvals_list

List approvals

ordinal_cpm_get

Get cpm

ordinal_cpm_update

Update cpm

ordinal_engagement_delete

Delete engagement

ordinal_idea_add_to_calendar

Idea add to calendar

ordinal_idea_archive

Archive idea

ordinal_idea_create

Create idea

Create an idea in the content backlog, optionally with draft content for LinkedIn, X, TikTok or YouTube Shorts. Returns the new idea with its id, url, title, channels and stored content. Use this to capture content before it is scheduled; use ordinal_idea_add_to_calendar to turn it into a post. Use ordinal_post_create to create a dated post directly.

Parameters

Name

Type

Required

Description

title

string

Required

Title of the idea.

campaign_id

string

Optional

UUID of the campaign to link the idea to.

label_ids

array

Optional

List of label UUIDs to attach to the idea. On update this replaces the existing labels.

object

Optional

LinkedIn content for the post, as an object. Fields: profileId (LinkedIn profile UUID, from ordinal_scheduling_profiles_list), copy (post text; mention people as @[Display Name](urn)), optional documentTitle, assets (list of objects with an assetId from the Uploads tools, up to 20 images, one video or one PDF), optional poll and linkPreview. Example: {"profileId": "550e8400-e29b-41d4-a716-446655440001", "copy": "Excited to announce our launch!"}

tiktok

object

Optional

TikTok content for the post, as an object. Required: profileId, copy (caption, up to 2,200 characters) and assets (exactly one video, as an object with assetId). Optional: privacyLevel (PUBLIC_TO_EVERYONE, FOLLOWER_OF_CREATOR, MUTUAL_FOLLOW_FRIENDS or SELF_ONLY), isCommentDisabled, isDuetDisabled, isStitchDisabled, isPromotingBusiness, isPaidPartnership and videoCoverTimestampMs. Example: {"profileId": "550e8400-e29b-41d4-a716-446655440005", "copy": "Behind the scenes", "assets": [{"assetId": "550e8400-e29b-41d4-a716-446655440014"}], "privacyLevel": "PUBLIC_TO_EVERYONE"}

object

Optional

X (Twitter) content for the post, as an object. Fields: profileId (X profile UUID, required) and tweets (required, at least one object with copy and optional assets of up to 4 assetId references; add several tweets in order to make a thread). Example: {"profileId": "550e8400-e29b-41d4-a716-446655440003", "tweets": [{"copy": "Big news today."}, {"copy": "More details below."}]}

youtube_shorts

object

Optional

YouTube Shorts content for the post, as an object. Required: profileId, title (up to 100 characters) and assets (exactly one video of 1 second to 3 minutes, as an object with assetId). Optional: description (up to 5,000 characters), privacyStatus (public, private or unlisted), categoryId, notifySubscribers, isEmbeddable and isSelfDeclaredMadeForKids. Example: {"profileId": "550e8400-e29b-41d4-a716-446655440006", "title": "Quick tip", "assets": [{"assetId": "550e8400-e29b-41d4-a716-446655440015"}], "privacyStatus": "public"}

ordinal_idea_get

Get idea

ordinal_idea_unarchive

Idea unarchive

ordinal_idea_update

Update idea

Update an idea's title, labels, campaign or per-channel content. Returns the updated idea with its id, url, title, channels and content. Send only the fields to change. Use ordinal_idea_get to read the current content first.

Parameters

Name

Type

Required

Description

idea_id

string

Required

ID of the idea (UUID).

campaign_id

string

Optional

UUID of the campaign to link the idea to.

label_ids

array

Optional

List of label UUIDs to attach to the idea. On update this replaces the existing labels.

object

Optional

tiktok

object

Optional

title

string

Optional

New title of the idea (at least one character).

object

Optional

youtube_shorts

object

Optional

ordinal_ideas_list

List ideas

ordinal_instagram_locations_search

Search instagram locations

ordinal_linkedin_followers_analytics_list

List linkedin followers analytics

ordinal_linkedin_profile_get

Get linkedin profile

ordinal_post_archive

Archive post

ordinal_post_comment_create

Create post comment

ordinal_post_comments_list

List post comments

ordinal_post_engagements_create

Create post engagements

ordinal_post_inline_comments_list

List post inline comments

ordinal_post_schedule

Post schedule

ordinal_post_subscribers_list

List post subscribers

ordinal_post_unschedule

Post unschedule

ordinal_post_version_content_get

Get post version content

ordinal_scheduling_profiles_list

List scheduling profiles

ordinal_slack_boost_delete

Delete slack boost

ordinal_subscribers_create

Create subscribers

ordinal_upload_get

Get upload

ordinal_users_list

List users

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Ordinal tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ordinal"], toolNames: [
    "ordinal_post_create",
    "ordinal_post_schedule",
    "ordinal_approvals_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Draft a LinkedIn post about our Series B, schedule it for Tuesday, and request approval from Dana" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ordinal"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Draft a LinkedIn post about our Series B, schedule it for Tuesday, and request approval from Dana" }],
  tools,
});

// Execute the tool call with the user's vaulted Ordinal access token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ordinal"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Draft a LinkedIn post about our Series B, schedule it for Tuesday, and request approval from Dana" }],
  tools,
});

// Tool call runs with the user's vaulted Ordinal access token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ordinal"] }, pageSize: 100,
});

const agent = new Agent({
  name: "social_media_agent",
  model: "gemini-2.5-pro",
  instruction: "Ordinal tools scoped to this user",
  tools,
});

await agent.run("Draft a LinkedIn post about our Series B, schedule it for Tuesday, and request approval from Dana");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Ordinal tool. Click to copy, paste into your agent, done.

Posts

Copy the prompt

Copied

Draft a LinkedIn post announcing our Series B.

Copy the prompt

Copied

Schedule the product recap post for Tuesday at 9am.

Copy the prompt

Copied

Unschedule tomorrow's X post until legal signs off.

Ideas and approvals

Copy the prompt

Copied

Add an idea to the backlog about our hiring week.

Copy the prompt

Copied

Request approval on the Series B post from Dana.

Copy the prompt

Copied

List approvals still pending this week.

Analytics and engagement

Copy the prompt

Copied

How did our LinkedIn posts perform last month?

Copy the prompt

Copied

Show daily X follower counts for September.

Copy the prompt

Copied

Plan team likes and reposts for the Series B post.

SEE HOW AUTH WORKS

Each user connects their own Ordinal access token once, and Scalekit sends it with every call. Tokens stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Ordinal

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Ordinal

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Ordinal

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Ordinal

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other social media and marketing connectors.

Engineering Teams

Auto release notes agent

Reads merged GitHub PRs, groups them into structured release notes, publishes the page to Notion, and announces the release in Slack. Every call runs on the engineer's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Ordinal access token looks fine in a demo. In production every scheduled post and approval looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Ordinal today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Ordinal as the user or through a shared token?

As the user. Each user connects their own Ordinal access token once, and Scalekit sends it with every call. Audit logs attribute every post, approval, and comment to that user, not a shared service account.

Where is the Ordinal access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Ordinal?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example drafting and analytics tools without ordinal_post_schedule or ordinal_label_delete. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Ordinal access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Is this Ordinal the social media planning tool?

Yes. This connector covers Ordinal, the platform for planning, approving, and scheduling posts on LinkedIn, X, Instagram, TikTok, and YouTube Shorts. It works in the workspace the user's access token belongs to, which ordinal_workspace_get returns.