Descript MCP connector for AI agents

Descript MCP tools for AI agents

CALL ANY TOOL

9 tools covering get, export, cancel.

descriptmcp_list_jobs

List jobs

List recent Descript jobs with optional filtering by project or job type.

Parameters

Name

Type

Required

Description

project_id

string

Optional

Filter by project UUID.

type

string

Optional

Filter by job type.

descriptmcp_get_project

Get project

descriptmcp_list_folders

List folders

descriptmcp_get_drive_info

Get drive info

descriptmcp_list_projects

List projects

descriptmcp_import_media

Import media

Import media into a Descript project from URLs (Google Drive, Dropbox, direct links) or direct file upload.

Parameters

Name

Type

Required

Description

add_media

object

Required

Map of display name → media entry. Keys can include folder paths (e.g. "Recordings/intro.mp4") to organize media into folders in the project. Each entry is one of: a URL import (provide "url"), a direct upload (provide "content_type" and "file_size"), or a multitrack sequence (provide "tracks" array). Use exactly one variant per entry. URL imports and direct uploads accept an optional "language" for transcription.

add_compositions

array

Optional

Compositions (timelines) to create from the imported media. Include this when creating a new project so media appears on the timeline. Omit when importing into an existing project unless the user asks to add to the timeline.

callback_url

string

Optional

Webhook URL for job completion.

folder_name

string

Optional

Folder path to place the new project in (e.g. "Clients/Acme/Videos"). Use "/" to separate nested folders. Only valid when creating a new project (no project_id). Existing folders along the path are reused; missing segments are created automatically. Requires team_access to be set to "edit", "comment", or "view" : projects in folders must be accessible to drive members.

project_id

string

Optional

UUID of an existing project. Mutually exclusive with project_name.

project_name

string

Optional

Name for a new project. Mutually exclusive with project_id.

team_access

string

Optional

Team access for new projects.

update_compositions

array

Optional

Append clips to existing compositions in the target project. Requires project_id.

workspace_name

string

Optional

Workspace to create the new project in, matched by name (case-insensitive). Only valid when creating a new project (no project_id). Reserved names: "Personal" (private space, requires team_access "none" or omitted) and "General" (shared drive workspace). "General" and custom workspaces require a shared team_access ("edit", "comment", or "view"); defaults to "view" when omitted. Custom workspaces require the caller to be a workspace member.

descriptmcp_export_timeline

Export timeline

descriptmcp_publish_project

Publish project

descriptmcp_export_transcript

Export transcript

descriptmcp_wait_for_job

Wait for job

descriptmcp_import_drive_media

Import drive media

descriptmcp_prompt_project_agent

Prompt project agent

descriptmcp_report_upload_status

Report upload status

descriptmcp_cancel_job

Cancel job

Build your Agent

Same auth pattern across every framework.

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="descriptmcp")

mcp = MultiServerMCPClient({
    "descriptmcp": {
        "url": "https://mcp.scalekit.com/descriptmcp",
        "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: "descriptmcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/descriptmcp
// 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: "descriptmcp" });

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

Try these prompts

Paste any prompt into your agent to get started.

Get started

Copy the prompt

Copied

Poll a Descript job until it completes, streaming progress updates, with an optional timeout?

Copy the prompt

Copied

Publish a Descript project composition as video or audio and return a shareable URL?

Advanced

Copy the prompt

Copied

Use Descript’s AI agent to query, create, or edit a project using a natural language prompt?

Copy the prompt

Copied

List Descript projects accessible to the authenticated user, with optional filtering and sorting?

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

Descript 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

Descript 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

Descript 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

Descript 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 connectors.

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.

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

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

One connector today. Ten 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 Descript as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Descript OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Descript?
Yes. Pass a tool name filter to listScopedTools so the media agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Descript.

What happens when a user revokes Descript 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.

Which Descript projects can the agent export or publish?
Only projects the authorizing user can access. Media imports, transcript exports, and publishes follow Descript drive membership, keeping client media isolated.

On this page

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