Niches · Advertising & campaign operations
Plan and create a campaign that can't spend until approved
One company's docs show a full fit.
What counts as done
A campaign, ad group or ad set and ads exist with the stated budget and targeting in a paused or draft state, the create was validated first, and nothing has spent; IDs returned for a person to review.
How agents ask for it: set up a search campaign for this product
, create a paused campaign with a $50 daily budget
, find keywords for this landing page
Does the job 1
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| Google Ads API BB Google LLC | Mutates take validate_only to check a request without making it, and campaigns take status PAUSED at creation; the reference warns status defaults to ENABLED if omitted, so the agent must set it. source |
Does the job, with a limit 7
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Amazon Ads API C Amazon.com Services LLC | The unified API's state enum includes DRAFT and PAUSED and creates return 207 with per-item results, but no validate-only mode exists beyond Sponsored Brands keyword reservations, and acc-12 found status values undocumented and state not persisting. source |
| Apple Ads Platform API C Apple Inc. | Campaigns take status PAUSED and report systemStatus and displayStatus, but no validate-only mode or test account was found, so a create can't be checked first and a retry can duplicate. source |
| LinkedIn Marketing APIs C LinkedIn Corporation | Campaigns can be created as DRAFT, not eligible to serve, or PAUSED, but some validation is postponed until activation, so a draft that passes may fail on launch, and no validate-only call was found. source |
| Meta Marketing API B Meta Platforms, Inc. | The MCP server's ads_create_campaign, ads_create_ad_set and ads_create_ad all create paused entities and ads_activate_entity is a separate tool, but no validate step is in the MCP tool list; REST validate_only is in the listing notes and wasn't reopened. source |
| Microsoft Advertising API C Microsoft Corporation | The listing notes say campaigns take Status Paused and PartialErrors report per item, but no validate-only mode exists, so a retried add can duplicate; the campaign reference wasn't reopened. source |
| Snapchat Ads API D Snap Inc. | Campaigns take status PAUSED, but no validate-only mode was found, so a retried create can duplicate, and the listing notes say PUT resets omitted attributes; the MCP server is read-only. source |
| X Ads API C X Corp. | MCP campaigns and line items are always created PAUSED and nothing spends until activated, but no validate-only mode was found, so a retried create can duplicate; the sandbox host is the place to rehearse. source |
Doesn't do this job 2
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| FetchIQ F LeadingResponse | Campaigns are bought through LeadingResponse's sales team and followed in the portal; no create endpoint exists. source |
| Refersion MCP D Refersion Inc. (New Jersey corporation, a subsidiary of EH ZO 1 Holdings LLC per its terms) | There are no ad campaigns, ad groups or budgets to create; the server manages affiliates, has and commissions. source |
What stops agents finishing
- no validate-only mode, so a retried create duplicates (Microsoft, Apple, Snap, X)
- MCP server that is read-only
- PUT that resets omitted fields (Snap, Apple arrays)
Around it
Before: web-scrapers.page-to-markdown, seo.keyword-research. After: human-in-the-loop.approval, advertising.performance-report.
Where this comes from
Weight 11 of 100 in Advertising & campaign operations: 3 of 28 counted mentions (acc-01, 15, 16); vendor MCP pages stress this job more than accounts do
The same as data: /api/v1/use-cases/advertising.launch-campaign.json, or the MCP tool get_use_case with id advertising.launch-campaign. Other jobs in this category: /api/v1/niches?category=advertising.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.