Motion MCP connector for AI agents

Tools your marketing agent reaches for on Motion, scoped per user.

CALL ANY TOOL

15 tools for ad creative analytics: rank your own creatives, pull AI summaries and video transcripts, and research competitor brands and their creatives.

motionmcp_get_ad_creative_map

Get ad creative map

Bulk export of every Meta ad with spend in a date range, mapped to its Motion creative asset. Use for programmatic or data-pipeline pulls (e.g. 'which ads share the same creative?'), not for performance analysis â use get_creative_insights for that. Each row is { adId, adName, adsetId, campaignId, creativeAssetId, launchDate, spend }. Ads that share a creativeAssetId run the same creative. Rows are sorted by spend descending. Pages hold up to 1000 rows (`limit`, default 1000). Pagination is offset-based: the response includes `pagination.totalCount` and `pagination.nextOffset`; to fetch everything, request offsets 0, limit, 2*limit, ... up to totalCount â these calls are independent and can run in parallel. If a page returns fewer rows than `limit` while `nextOffset` is non-null, also fetch from `nextOffset` so no rows are skipped. Keep the date range and limit identical across pages. If the report is still compiling, the tool returns `status: 'waiting'` with `pollAfterMs`; call again with identical params. Ads without a resolved creative asset and catalog/feed (dynamic product) ads are excluded. The request may write private compilation state and enqueue an internal report job over stored Motion data, but it does not start a live Facebook report. This call records private operational logs and usage telemetry.

Parameters

Name

Type

Required

Description

organizationId

string

Required

The organization ID from get_auth_context

workspaceId

string

Required

The workspace ID from get_auth_context

datePreset

string

Optional

Predefined date range. Omit if using startDate/endDate. One of: `TODAY`, `YESTERDAY`, `THIS_MONTH`, `LAST_MONTH`, `LAST_7_DAYS`, `LAST_14_DAYS`, `LAST_30_DAYS`, `LAST_90_DAYS`, `CUSTOM`.

endDate

string

Optional

Custom end date (YYYY-MM-DD). Requires datePreset=CUSTOM.

limit

integer

Optional

Rows per page, up to 1000. Default: `1000`.

offset

integer

Optional

Zero-based row offset. Use multiples of limit; pages can be requested in parallel. Default: `0`.

startDate

string

Optional

Custom start date (YYYY-MM-DD). Requires datePreset=CUSTOM.

motionmcp_get_auth_context

Get auth context

motionmcp_get_brand_by_domain

Get brand by domain

motionmcp_get_creative_insights

Get creative insights

Retrieve creative performance insights for your own ads in a workspace. Either datePreset or both startDate and endDate must be provided.

Parameters

Name

Type

Required

Description

insightType

string

Required

Primary metric to sort/rank creatives by. One of: `SPEND`, `SCALING`, `HOOK`, `ROAS`, `PURCHASES`, `PURCHASE_VALUE`, `CTR_ALL`, `CPA`, `CPC`.

organizationId

string

Required

The organization ID from get_auth_context

workspaceId

string

Required

The workspace ID from get_auth_context

chartKPIs

array

Optional

Optional KPI fields to include in chart KPI metrics.

clickAttributionWindow

string

Optional

Override the workspace Meta click attribution window, e.g. "1d_click" or "7d_click". One of: `1d_click`, `7d_click`, `28d_click`, `skan_click`.

creativeAssetIds

array

Optional

Optional creative asset IDs to narrow results.

cursor

string

Optional

Opaque cursor from the previous response. Reuse all other query parameters unchanged.

datePreset

string

Optional

Predefined date range. Omit if using startDate/endDate. One of: `TODAY`, `YESTERDAY`, `THIS_MONTH`, `LAST_MONTH`, `LAST_7_DAYS`, `LAST_14_DAYS`, `LAST_30_DAYS`, `LAST_90_DAYS`, `CUSTOM`.

endDate

string

Optional

Custom end date (YYYY-MM-DD). Requires datePreset=CUSTOM.

filters

array

Optional

Nested filter groups to narrow which creatives are returned. Outer array = AND (all groups must pass); inner array = OR (any filter in a group can match). For text fields (campaignName, adsetName, adName): use "value" (singular) for case-insensitive substring match, or "values" (array) for exact match. For metric fields: set "metric": true and use "value" for thresholds or "values" for ranges. Example: [[{"field":"spend","type":"GREATER_THAN","value":"100","metric":true}],[{"field":"campaignName","type":"includes","value":"Prospecting"}]] returns creatives where spend > 100 AND campaign name contains "Prospecting".

groupBy

string

Optional

How to group ranked rows. Options: 'creative' (default â one row per creative asset), 'adId' (one row per ad â for ad-level optimization, comparing same creative across ad sets, deciding which ad to pause/scale), 'name' (by ad name), 'copy' (by ad body text â 'which copy performs best?'), 'headline' (by headline text), 'landingPage' (by destination URL â 'which landing page converts best?'). One of: `creative`, `adId`, `name`, `copy`, `headline`, `landingPage`.

includeCreativeUrls

boolean

Optional

Include public creative URLs for the interactive gallery. Defaults true; set false only for text-only output. Default: `true`.

includeEntityCategoryValues

boolean

Optional

Include the full taxonomy catalog (all possible values) per glossary category. Default false â only the values applied to each creative are returned. Set true when you need to see all available tags for coverage gap analysis. Default: `false`.

includeGlossary

boolean

Optional

Include creative taxonomy/glossary tags per creative. Default false to minimize payload. Set true for creative pattern analysis. Default: `false`.

includeNorthbeam

boolean

Optional

Include Northbeam attribution metrics when the workspace has a Northbeam connection. Only supported with groupBy "adId" or "name". Default: `false`.

insightGroups

array

Optional

Metric groups per creative. Defaults: spendState, performance, motion, click.

limit

integer

Optional

Requested rows per page. The tool caps each page at 25 rows; use nextCursor to retrieve additional pages. Default: `25`.

startDate

string

Optional

Custom start date (YYYY-MM-DD). Requires datePreset=CUSTOM.

tableKPIs

array

Optional

Optional KPI fields to include in table KPI metrics.

viewAttributionWindow

string

Optional

Override the workspace Meta view attribution window, e.g. "1d_view" or "7d_view". One of: `1d_view`, `7d_view`, `28d_view`, `skan_view`.

withAggregatedInsights

boolean

Optional

Include account-level aggregated metrics. Default: `false`.

motionmcp_get_creative_summary

Get creative summary

motionmcp_get_creative_transcript

Get creative transcript

motionmcp_get_demographic_breakdown

Get demographic breakdown

motionmcp_get_glossary_values

Get glossary values

motionmcp_get_inspo_brand_context

Get inspo brand context

motionmcp_get_inspo_creatives

Get inspo creatives

motionmcp_get_reports

Get reports

motionmcp_get_workspace_brand

Get workspace brand

motionmcp_get_workspace_competitors

Get workspace competitors

motionmcp_search_brands

Search brands

motionmcp_submit_feedback

Submit feedback

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);

// Motion MCP tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["motionmcp"], toolNames: [
    "motionmcp_get_auth_context",
    "motionmcp_get_creative_insights",
    "motionmcp_get_creative_summary"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Rank our ad creatives by spend for the last 30 days" }] });

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: ["motionmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Rank our ad creatives by spend for the last 30 days" }],
  tools,
});

// Execute the tool call with the user's vaulted Motion credential
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: ["motionmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Rank our ad creatives by spend for the last 30 days" }],
  tools,
});

// Tool call runs with the user's vaulted Motion credential
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: ["motionmcp"] }, pageSize: 100,
});

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

await agent.run("Rank our ad creatives by spend for the last 30 days");

Try these prompts

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

Creative performance

Copy the prompt

Copied

Rank my ad creatives by ROAS for the last 14 days.

Copy the prompt

Copied

Summarize the top-spending video creative from this month.

Copy the prompt

Copied

Pull the transcript for my best-performing video ad.

Audiences and reports

Copy the prompt

Copied

Break down last month's ad performance by age and gender.

Copy the prompt

Copied

List the saved reports in my workspace.

Copy the prompt

Copied

Show the glossary tags my workspace uses to label creatives.

Competitor research

Copy the prompt

Copied

List the competitor brands my workspace tracks.

Copy the prompt

Copied

Show active creatives these competitors launched in the last 30 days.

Copy the prompt

Copied

Get the brand positioning and messaging angles for example.com.

SEE HOW AUTH WORKS

Each user signs in to Motion once; Scalekit stores and refreshes their tokens. Every call is scope checked, and every action is logged.

Authorize

Your user connects

Motion MCP

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

Motion MCP

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

Motion MCP

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

Motion MCP

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 marketing and analytics connectors.

Support and Ops Teams

Email-to-calendar agent

Reads scheduling intent out of Gmail threads, resolves the times everyone actually has free, and creates the event on the user's own Google Calendar. No shared service account.

Gmail

Google Calendar

View agent

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

GTM and RevOps Teams

Sales call prep agent

Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Motion token looks fine in a demo. In production every creative report 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.

Motion 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 Motion as the user or through a shared key?

As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every Motion query in your audit trail is attributed to a real user, not a shared service account.

Where is the Motion token stored?

Each user signs in to Motion once; Scalekit stores and refreshes their tokens. The credential sits in an AES-256 encrypted vault with per-tenant namespacing, is resolved at request time, never enters LLM context, and can be revoked from one dashboard.

Can I limit what the agent does in Motion?

Yes. Filter by tool name in listScopedTools to expose only what you want. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

What can the agent do with Motion MCP?

Motion MCP has 15 tools: 14 read and 1 write. Your agent can rank your own ad creatives, pull AI summaries and video transcripts, break down performance by age and gender, open saved reports, and research competitor brands and their creatives. Start with motionmcp_get_auth_context, which returns the workspaceId the other tools need.