Turn recurring marketing work into one connected operation across research, content, campaigns, localization, publishing, and reporting.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
This server may ask you to sign in when your AI client connects.
Last probed Nov 3, 2026 · mcp.dng.ai
24tools discovered
For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://mcp.dng.ai/mcp
Skill page: https://www.mcpbundles.com/skills/dng-mcp-c681fb168d
Explore capabilities (24)
read 11
write 9
other 4
Get
9
Create
3
Delete Brandkit
3
Update
3
Generate
2
List
2
Other capabilities
2
List Workflows
read
list_workflows
List all workflows accessible to the current user.
Returns a list of workflows with their IDs, names, descriptions, and metadata.
Use this to discover available workflows before getting details or running them.
Returns:
List of workflows with id, name, description, state, and user info.
List Workflows — List all workflows accessible to the current user.
Returns a list of workflows with their IDs, names, descriptions, and metadata.
Use this to discover available workflows before getting details or running them.
Returns:
List of workflows with id, name, description, state, and user info.
Get Workflow — Get a workflow's description and schema to understand its required inputs.
IMPORTANT: Call this tool BEFORE running a workflow to understand what inputs
are required and their expected format.
Args:
workflow_id: The ID of the workflow to fetch
Returns:
Workflow description including input node definitions. Look for nodes with
input types (e.g., Text, Image, File) to understand what inputs are needed
for run_workfl
Create Workflow — Create a new workflow.
Args:
name: Name for the new workflow (must be unique within the organization)
description: Optional description of the workflow's purpose
instruction: Optional instruction text for the workflow
data: Optional workflow graph data (nodes, edges, viewport). Defaults to
an empty dict if not provided.
Returns:
The created workflow object with its ID and metadata.
Update Workflow — Update an existing workflow.
Only provided (non-None) fields will be updated; omitted fields remain unchanged.
Args:
workflow_id: The ID of the workflow to update
name: New name for the workflow
description: New description for the workflow
instruction: New instruction text for the workflow
data: New workflow graph data (nodes, edges, viewport)
Returns:
The updated workflow object.
Run Workflow — Run a DNG workflow by ID.
IMPORTANT: Before calling this tool, use get_workflow to fetch the workflow
description and understand what inputs are required.
Args:
workflow_id: The ID of the workflow to run
inputs: Input parameters as a dictionary mapping node IDs to their values.
Format: {"node_id": {"value": "...", "type": "..."}, ...}
Example: {"Text_0": {"value": "hello world", "type": "text"},
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Turn recurring marketing work into one connected operation across research, content, campaigns, localization, publishing, and reporting.
How do I connect Draft & Goal to my AI agent?
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
How many tools does Draft & Goal provide?
Operate this server?
Request removal if you do not want Draft & Goal listed here, or claim the listing if you want to manage it on MCPBundles.
Operate Draft & Goal?
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms · Request removal
More in marketing
Other MCP servers in this category from the directory index
Get Workflow Run Status — Poll the status and results of a workflow run.
Use this to check if a run has completed, failed, or is still in progress.
When the run is done, the response includes completed steps with their outputs.
A status code of 250 means the run is still in progress.
Args:
run_id: The workflow run ID returned by run_workflow
Returns:
Run status including state (TO_START, IN_PROGRESS, DONE, FAILED, etc.),
completed step outputs
Get Dashboard Analytics — Get dashboard KPIs: success rate, average execution time, top workflows, and execution volume.
Args:
period: Time period for analytics - "current_day", "7_days", or "30_days"
view_as: Role perspective - "admin" (all org data), "builder" (own + shared), or "runner" (shared only)
Returns:
Analytics including total_workflows, runs_today, success_rate, avg_execution_time,
top_workflows, and execution_volume_over_time.
Get Recent Runs — Get recent workflow runs sorted by most recent first, with pagination.
Args:
view_as: Role perspective - "admin", "builder", or "runner"
page: Page number (1-based)
page_size: Number of items per page (1-50)
Returns:
Paginated list of recent runs with id, workflow_id, workflow_name, state,
started_at, and updated_at.
Get Active Workflows Count — Get the count of active workflows that have production versions.
An active workflow must have state=ACTIVE and at least one production
workflow version (isProduction=true).
Returns:
Count of active workflows and the organization ID.
Get Monthly Workflow Run Count — Get the total number of workflow runs for the current or last month.
Excludes user-aborted runs from the count.
Args:
period: "current_month" or "last_month"
Returns:
Workflow run count with period start/end dates and label.
Generate Workflow — Generate or modify a DNG workflow via a multi-turn AI agent conversation.
This is a CONVERSATIONAL tool — the AI agent may ask clarifying questions
before producing a workflow. You must call this tool multiple times until
the response indicates completion.
## Conversation flow
1. **First call**: Send the user's request with NO session_id to start a
new generation session.
2. **Check the response status**:
- `status: "waitin
Save Generated Workflow — Save a completed generated workflow to your DNG workspace.
Call this after generate_workflow returns `complete: true`. The workflow
data is cached server-side — you only need to provide the session_id.
Args:
session_id: The session_id from the completed generate_workflow call.
name: Name for the workflow. Defaults to the AI-suggested name if omitted.
description: Optional description of the workflow's purpose.
Returns:
List Brandkits — List all brand kits for the current organization.
Returns:
List of brand kits, each with id, name, createdAt, updatedAt and
the five V2 data sections (basicInformation, brandIdentity,
audience, contentStrategy, styleAndVoice).
Get Brandkit — Get a brand kit by ID.
Args:
brandkit_id: The ID of the brand kit to fetch.
Returns:
The brand kit: id, name, createdAt, updatedAt, and the five V2
sections. `audience.buyerPersonas` holds buyer personas (each with
a server-generated `id`) — use the persona tools to modify them.
Get Brandkit Catalog — List the brand-kit variables exposed by the BrandKit Variables node.
Static, code-level metadata — the same for every user. Use this to
discover which `{{brandkit.*}}` variables a workflow can reference
before wiring a BrandKit Variables node.
Returns:
The variable catalog (keys, labels, and the section each maps to).
Get Brandkit Limit — Get the brand-kit quota for the current organization.
Check this before create_brandkit to know whether the org can add
another kit.
Returns:
The org's brand-kit limit (used vs. maximum allowed).
Create Brandkit — Create a new brand kit (V2 schema).
IMPORTANT: If the user only provides a URL, use
`generate_brandkit_from_url` first — it auto-detects brand info — then
pass the result here to persist it. Use this tool directly only when
the user supplies the brand details themselves.
All URL fields (brand_url, logo, favicon, competitor values) must be
https:// — the API rejects http:// and private/reserved IPs.
Args:
name: Display name fo
Update Brandkit — Update a brand kit (V2). Only provided fields change; the rest is
preserved.
The server replaces each PATCHed section wholesale, so this tool first
fetches the current kit and deep-merges your fields into the existing
sections before sending. Buyer personas are NOT edited here — use
create_brandkit_persona / update_brandkit_persona / delete_brandkit_persona.
See create_brandkit for the meaning of each field. URL fields must be
https://.
Delete Brandkit — Delete a brand kit.
Cannot delete a brand kit that is currently used by a workflow.
Args:
brandkit_id: The ID of the brand kit to delete.
Returns:
Success confirmation, or an error if the brand kit is in use.
Create Brandkit Persona — Add a buyer persona to a brand kit's audience.
The server assigns the persona's `id` — do not pass one.
Args:
brandkit_id: The ID of the brand kit.
name: Persona display name (required).
description: Who this persona is.
image: https URL to a persona image.
quote: A representative quote.
demographics: {"age": str, "location": str, "familyStatus": str,
"educationLevel": str, "incomeLevel": st
Update Brandkit Persona — Update a buyer persona. Only provided fields change.
See create_brandkit_persona for field shapes. Note: nested objects
(demographics, communication) and lists are replaced wholesale, not
field-merged — pass the full object you want stored.
Args:
brandkit_id: The ID of the brand kit.
persona_id: The ID of the persona to update.
(other args: same as create_brandkit_persona; omit to leave unchanged)
Returns:
Delete Brandkit Persona — Delete a buyer persona from a brand kit.
Args:
brandkit_id: The ID of the brand kit.
persona_id: The ID of the persona to delete.
Returns:
The updated brand kit object.
Generate Brandkit From Url — Auto-generate a brand kit template from a website URL.
This is the DEFAULT tool when the user provides a URL and asks to
create a brand kit. It scrapes the site and uses AI to extract brand
name, description, customer profile, competitors, point of view, tone
of voice, logo, and favicon.
The result is an UNSAVED template — pass its fields to create_brandkit
to persist it.
Args:
url: The website URL (must be https://).
Delete Brandkit Asset — Delete an uploaded brand-kit asset (logo / favicon / persona image).
Removes both the stored file and its DB row. Note: this does not clear
any pointer to it in the brand-kit data (e.g. basicInformation.logo) —
update that separately with update_brandkit if needed.
Args:
brandkit_id: The ID of the brand kit the asset belongs to.
asset_id: The ID of the asset to delete.
Returns:
Success confirmation.
MCPBundles probed 24 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
What authentication does Draft & Goal require?
Draft & Goal may require signing in to the provider before tools can run. Connect through MCPBundles or your MCP client and complete any provider login when prompted.
Don't want this listed?
Request removal from the MCPBundles directory. We stop publishing this listing on mcpbundles.com.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.