Motion MCP connector for AI agents

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

CALL ANY TOOL

Each tool maps to a Motion API resource and runs under the authorizing user's API key.

motionmcp_get_auth_context

Get Auth Context

Retrieve the authenticated user's organizations and workspaces. Returns the workspaceId required by all other Motion tools.

Parameters

Name

Type

Required

Description

—

No parameters required

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

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.

creativeAssetIds

array

Optional

Optional creative asset IDs to narrow results.

datePreset

string

Optional

Predefined date range. Omit if using startDate/endDate.

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 — one row per creative asset), 'adId' (one row per ad — 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 — 'which copy performs best?'), 'headline' (by headline text), 'landingPage' (by destination URL — 'which landing page converts best?').

includeEntityCategoryValues

boolean

Optional

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

includeGlossary

boolean

Optional

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

insightGroups

array

Optional

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

limit

integer

Optional

Max number of creatives to return

startDate

string

Optional

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

tableKPIs

array

Optional

Optional KPI fields to include in table KPI metrics.

withAggregatedInsights

boolean

Optional

Include account-level aggregated metrics

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

One auth pattern wires Motion into LangChain, OpenAI, Anthropic, and Google ADK without framework-specific token handling.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="motionmcp")

mcp = MultiServerMCPClient({
    "motionmcp": {
        "url": "https://mcp.scalekit.com/motionmcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

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

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "motionmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/motionmcp
// Pass: Authorization: Bearer + token

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

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "motionmcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/motionmcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="motionmcp")
# Connect to MCP at https://mcp.scalekit.com/motionmcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your Motion agent to get started.

Task triage

Copy the prompt

Copied

List all tasks assigned to me that are overdue or due today.

Copy the prompt

Copied

Show me every high-priority task across all my active projects.

Copy the prompt

Copied

What tasks have no due date assigned to them in my current projects?

Copy the prompt

Copied

Create a new ASAP task called 'Prep board slides' in the Q3 Launch project due Friday.

Project overview

Copy the prompt

Copied

Summarise the status of all my active projects and how many open tasks each has.

Copy the prompt

Copied

List all users in my workspace and what projects they are assigned to.

Copy the prompt

Copied

How many tasks in the Client Onboarding project are still marked todo?

Schedule and planning

Copy the prompt

Copied

Show me my AI-generated schedule for today and flag any timeblocked tasks past their due date.

Copy the prompt

Copied

Move all overdue tasks in Engineering Backlog to due next Monday.

Copy the prompt

Copied

What does my schedule look like for tomorrow?

SEE HOW AUTH WORKS

The user authorises once with their Motion API key. Every agent call after uses that key, scoped to the tools you allow.

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 productivity connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought — shared keys, no scope enforcement, no audit trail.

01.

Shared tokens break per-user analytics

A shared Motion API key looks fine in a demo. In production every task creation and schedule update shows as a service account. Scalekit resolves the real user's credential so Motion audit logs carry the correct author and AI-scheduled actions are attributed to the right person.

// shared token
motion audit → bot_service_account

// scalekit
motion audit → alice@acme.com ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Motion MCP today. Others 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 every user need their own Motion API key, or can I use one shared key?

Every user connects their own Motion API key. Scalekit vaults each key under a per-user, per-tenant namespace. A shared key collapses all task creations, schedule updates, and project edits into a single audit identity and breaks any per-user access controls Motion enforces on your workspace.

How does Scalekit store the Motion API keys?

Keys are encrypted at rest with AES-256 and resolved at request time directly into the tool call. The plaintext key never appears in agent context, logs, or LLM prompts. You can rotate or revoke a key from the Scalekit dashboard without redeploying your agent.

Can I limit which Motion tools a specific agent or tenant can call?

Yes. Use listScopedTools to return only the tools permitted for a given user or tenant. Your agent never sees tools outside the allowed scope, so it cannot accidentally call motion_task_create when only read access is granted. Scope lists update at runtime without redeployment.

What happens when a user revokes their Motion API key or leaves the organisation?

Scalekit detects the 401 on the next tool call and surfaces a re-auth event to your application. The agent stops executing Motion tools for that user until a fresh key is vaulted. No other users or tenants are affected. You can also proactively delete a user's credential via the Scalekit API when offboarding.

Motion's AI auto-schedules tasks — will agent-created tasks get scheduled automatically?

Yes. Tasks created via motion_task_create go into the authenticated user's Motion inbox and are subject to Motion's AI scheduling engine, just as if the user created them directly. Your agent sets the priority and due date; Motion's scheduler handles when the task appears in the user's timeblocked calendar.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit