Category · Communication
Advertising platform APIs for AI agents
The advertising platforms' own APIs for campaigns, budgets, audiences and performance reports. Compared on what an agent can read and change, the approval needed for access, rate limits and how a change can be checked before it spends money.
Best advertising platform APIs for AI agents, the shortlist45 head-to-head comparisons
Capability keys ads.reporting · ads.campaigns · ads.budgets · ads.audiences · ads.creatives · All tools
letme.dev/ads.reporting picks the top-graded tool in this list and says how to call it direct (how letme works).
The same listing from the live API. Graded results come first, then the official MCP registry when no graded-only filter is set.
https://www.anchorterminal.com/api/v1/search
Filters
| Compare | # | Tool | Category | Grade | Score | Agent rating | p95 | Context | Price / x402 | Auth | Where | Details |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 76 | Google Ads APIGoogle · HTTP API | Advertising | BB | 77.1 | 3.5 (4) | n/a | n/a | Free | OAuth | Hosted and local | ||
|
Google's API for managing Google Ads accounts, campaigns, budgets, audiences, ads and performance reports over gRPC or REST, with OAuth 2.0 access. Google also publishes an open-source, read-only MCP server that runs Google Ads Query Language reports. Top strength
Top weakness One OAuth scope, |
||||||||||||
| 383 | Meta Marketing APIMeta · HTTP API | Advertising | B | 68.4 | 2.8 (4) | n/a | n/a | Free | OAuth | Hosted | ||
|
Meta's Marketing API creates and manages campaigns, ad sets, ads, creatives and audiences across Facebook, Instagram, Messenger and WhatsApp, and reports performance through Ads Insights. It is a versioned Graph API with OAuth access tokens. Top strength
Top weakness Default Limited access allows a score of 60 per ad account (read 1, write 3) and blocks for 300 seconds at the limit |
||||||||||||
| 769 | LinkedIn Marketing APIsLinkedIn Corporation · HTTP API | Advertising | C | 60.5 | 2.8 (4) | n/a | n/a | Free | OAuth | Local | ||
|
LinkedIn's advertising APIs for campaign management, performance reporting, matched audiences, conversions and lead sync. Agents call versioned REST endpoints at api.linkedin.com/rest with a member's OAuth token, after LinkedIn approves the developer application. Top strength Monthly versions (latest 202610) each supported for at least one year, with a sunset date per version on the migrations page Top weakness Standard rate limits are not published. An app sees its limit in the Developer Portal only after calling the endpoint |
||||||||||||
| 785 | Microsoft Advertising APIMicrosoft · HTTP API | Advertising | C | 60.2 | 3.0 (4) | n/a | n/a | Free | OAuth | Hosted | ||
|
Microsoft's API for Microsoft Advertising (formerly Bing Ads) search, shopping and audience campaigns. It covers campaign management, bulk upload and download, reporting, ad insight, billing and account management over REST and SOAP. Top strength Sandbox with its own endpoints, a shared developer token (BBD37VB98) and sign-up that skips payment information. Ads created there are never served Top weakness Call-rate limits carry no numbers. The docs describe a 60-second sliding window, and call the Bulk and Reporting limits internal and subject to change |
||||||||||||
| 849 | X Ads APIX Corp. · HTTP API | Advertising | C | 58.7 | none | n/a | n/a | Free | OAuth | Hosted | ||
|
X's Ads API creates and manages campaigns, line items, targeting, creatives and audiences on X and returns performance analytics. Agents call versioned REST endpoints at ads-api.x.com with OAuth 1.0a, or use the X Ads MCP server with OAuth 2.0. Top strength Rate limits are published by endpoint type, such as 450 writes a minute and 250 synchronous analytics requests per 15 minutes, with remaining quota in Top weakness No OpenAPI file covers the Ads API. The published file (version 2.170, 178 paths) describes api.x.com only |
||||||||||||
| 984 | Amazon Ads APIAmazon · HTTP API | Advertising | C | 55.4 | none | n/a | n/a | Free | OAuth | Hosted | ||
|
Amazon's REST API for its advertising products, covering campaigns, budgets, targets, audiences, creative assets and performance reports for sponsored ads and Amazon DSP. An Amazon Ads MCP Server in open beta exposes the same operations as tools. Top strength OpenAPI 3.0.1 files for the Unified API in Amazon's docs repository, 97 operations with typed inputs and a 49-value ErrorCode enum Top weakness Access needs an approved application and an advertiser's consent in a browser |
||||||||||||
| 1014 | Apple Ads Platform APIApple · HTTP API | Advertising | C | 54.4 | none | n/a | n/a | Free | OAuth | Hosted | ||
|
Apple's Ads Platform API creates and manages App Store and Apple Maps campaigns, ad groups, keywords, ads, creatives and budgets, and returns performance reports. Agents call REST endpoints at api.ads.apple.com/v1 with an OAuth 2 client credentials token. Top strength Every response carries Top weakness The Platform API was first released in August 2026 and its changelog has one entry. The Campaign Management API 5 it replaces is sunset on 26 January 2027 |
||||||||||||
| 1057 | Refersion MCPRefersion Inc. · MCP server | Advertising | D | 53.2 | none | n/a | n/a | $39 / mo | OAuth | Hosted | ||
|
Refersion's remote MCP server connects Claude, ChatGPT, Gemini and other MCP clients to a merchant's Refersion account over OAuth, so an assistant can review conversions, manage affiliates and offer settings, credit missing commissions and find new affiliates. Top strength OAuth with PKCE S256 and 20 scopes split by area and by read or write, each of which can be unticked at consent, per Refersion Top weakness MCP tool names, input schemas and annotations aren't published and can be read only after signing in |
||||||||||||
| 1118 | Snapchat Ads APISnap Inc. · HTTP API | Advertising | D | 51.7 | none | n/a | n/a | Free | OAuth | Hosted | ||
|
Snap's Ads API creates and manages Snapchat campaigns, ad squads, ads, creatives and audiences and returns performance statistics. Agents call REST endpoints at adsapi.snapchat.com/v1 with a member's OAuth token, or read account data through the read-only Ads MCP server. Top strength llms.txt at developers.snap.com indexes every Marketing API page, and each page has a Markdown twin at the same path with Top weakness No OpenAPI specification, Postman collection or Ads API SDK was found in the reviewed documentation |
||||||||||||
| 1551 | FetchIQNot for agents LeadingResponse · Platform | Advertising | F | 7.8 | 1.3 (4) | n/a | n/a | Paid | OAuth or key | Local | ||
|
FetchIQ is LeadingResponse's web portal where its clients, such as financial advisers, plan and track seminar, webinar and lead-generation campaigns, with event check-in, consumer profiles and a built-in assistant called GidgetAI. Used by people through a browser. Top strength Launch dated first-hand on 19 October 2026, with client migration from Hub explained Top weakness No API, MCP server, webhooks or developer docs found |
||||||||||||
Nothing matches these filters. .
p95 latency and context cost come from our probes, which haven't run yet, so those columns start hidden. Grades run from AA to F, and agent-ready means BB or better. Filters, sorting and export run in your browser; the table is complete without JavaScript.
How we test this category
One test account on each platform. The same tasks run through its API (read last month's performance by campaign, create a paused campaign with a budget, change a bid, build an audience). We check the access steps, validation before a change is live and reporting delay. In this run listings are graded from public evidence against the published checklist.
How the ranking works
Every tool is scored 0 to 100 across 9 weighted categories, minus deductions for negative events, and given a grade from AA to F. Reliability, latency and context cost are measured by probes and by traffic through letme. Schema quality, security and payments are assessed against a published checklist. Task success comes from a fixed task suite. Payments, including x402, are one category of the nine. Read the methodology.
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.