AdMakeAI

AI ad-creative platform for Meta, Instagram, and TikTok that turns product photos or prompts into finished ad images and UGC-style video ads, batch-generates ad-set variations, generates ad copy, researches competitor ads from the Meta Ad Library, reads Meta campaign analytics, and drafts and publishes campaigns through the official Meta Marketing API. Its machine-readable contract is not an OpenAPI: AdMakeAI is a tRPC application projected two ways, as a hosted streamable-HTTP MCP server at /api/mcp and as 1:1 REST procedure paths at /api/v1, both bound to one account and one credit pool. It implements the full MCP authorization stack (RFC 8414, RFC 9728, RFC 7591, PKCE S256) with three scopes filtered at tools/list, publishes an llms.txt, an MCP server card and an agent-skills index under /.well-known/, and ships a first-party Agent Skill for coding agents.

AdMakeAI publishes 3 APIs on the APIs.io network. Tagged areas include Advertising, Marketing, AdTech, Generative AI, and Image Generation.

AdMakeAI’s developer surface includes authentication, documentation, API reference, getting-started guide, support, engineering blog, pricing, and 19 more developer resources.

39.4/100 thin ▬ flat Agent 29/100 agent aware Full breakdown ↓
scored 2026-08-17 · rubric v0.11.0
3 APIs 2 MCP Servers
AdvertisingMarketingAdTechGenerative AIImage GenerationVideo GenerationMeta AdsCompetitive IntelligenceMCPAgentsAgent Skills

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-17 · rubric v0.11.0
Composite quality — 39.4/100 · thin
Contract Quality 0.0 / 25
Developer Ergonomics 11.7 / 20
Commercial Clarity 15.3 / 20
Operational Transparency 2.7 / 13
Governance 1.5 / 12
Discoverability 8.2 / 10
Agent readiness — 29/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 10 / 10
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/admakeai: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 3

Individual APIs this provider publishes, each with its own machine-readable definition.

AdMakeAI REST API

RPC-style JSON REST API with dot-named tRPC procedure paths (e.g. adGeneration.create) covering ad image and UGC video generation, batch ad sets, ad copy, competitor ad research...

AdMakeAI MCP Server

Hosted, stateless streamable-HTTP MCP server exposing 65 tools across account, projects, uploads, ad image generation, ad copy, ad sets, UGC video, competitor research, Meta pub...

AdMakeAI Agent Skill

Published SKILL.md that teaches an agent tool selection from natural-language intent, credit mechanics, pagination, destructive-action confirmation, and prompt patterns for ad c...

MCP Servers 2

Model Context Protocol servers that expose these APIs to AI agents.

mcp

MCP SERVER

admakeai-mcp.yml

MCP SERVER

Pricing Plans 1

Published pricing tiers and plan structures.

Rate Limits 1

Documented rate limits and quota policies.

Admakeai Rate Limits

2 limits

RATE LIMITS

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Admakeai Authentication

apiKey/http/oauth2 · 3 schemes

SECURITY

Admakeai Domain Security

TLSv1.3

SECURITY

Scopes 1

OAuth scopes governing access to this provider's APIs.

Admakeai Scopes

4 scopes · authorizationCode

4 scopes

SCOPES

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Admakeai Agentic Access

65 operations

65 operations · 0 acting

AGENTIC

Resources

Get Started 3

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 4

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Build 2

SDKs, sample code, and the tooling you integrate with

Access & Security 3

Authentication, authorization, and security posture

Operate 2

Status, limits, changes, and where to get help

Commercial 4

Pricing, plans, and the legal terms of use

Company 1

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
name: AdMakeAI
description: 'AI ad-creative platform for Meta, Instagram, and TikTok that turns product photos or prompts into finished ad
  images and UGC-style video ads, batch-generates ad-set variations, generates ad copy, researches competitor ads from the
  Meta Ad Library, reads Meta campaign analytics, and drafts and publishes campaigns through the official Meta Marketing API.
  Its machine-readable contract is not an OpenAPI: AdMakeAI is a tRPC application projected two ways, as a hosted streamable-HTTP
  MCP server at /api/mcp and as 1:1 REST procedure paths at /api/v1, both bound to one account and one credit pool. It implements
  the full MCP authorization stack (RFC 8414, RFC 9728, RFC 7591, PKCE S256) with three scopes filtered at tools/list, publishes
  an llms.txt, an MCP server card and an agent-skills index under /.well-known/, and ships a first-party Agent Skill for coding
  agents.'
image: https://admakeai.com/apple-touch-icon.png
url: https://admakeai.apievangelist.com/apis.yml
created: '2026-08-11'
modified: '2026-08-11'
specificationVersion: '0.21'
tags:
- Advertising
- Marketing
- AdTech
- Generative AI
- Image Generation
- Video Generation
- Meta Ads
- Competitive Intelligence
- MCP
- Agents
- Agent Skills
apis:
- name: AdMakeAI REST API
  description: 'RPC-style JSON REST API with dot-named tRPC procedure paths (e.g. adGeneration.create) covering ad image and
    UGC video generation, batch ad sets, ad copy, competitor ad research, Meta analytics, and Meta campaign draft publishing.
    POST bodies are JSON; GET inputs go in ?input=<URL-encoded JSON>; responses are wrapped as { ok, tool, data }. Authenticated
    via an x-api-key header (or Authorization: Bearer). Every MCP tool is reachable here 1:1. No OpenAPI is published.'
  humanURL: https://admakeai.com/agents
  baseURL: https://admakeai.com/api/v1
  tags:
  - Advertising
  - Marketing
  - AdTech
  - Generative AI
  - Image Generation
  - Video Generation
  - Meta Ads
  - Competitive Intelligence
  - MCP
  - Agents
  - Agent Skills
  properties:
  - type: Documentation
    url: https://admakeai.com/api/docs
  - type: APIReference
    url: https://admakeai.com/api/docs
  - type: Authentication
    url: authentication/admakeai-authentication.yml
  - type: Conventions
    url: conventions/admakeai-conventions.yml
  - type: ErrorCatalog
    url: errors/admakeai-error-codes.yml
  - type: DataModel
    url: data-model/admakeai-data-model.yml
- name: AdMakeAI MCP Server
  description: Hosted, stateless streamable-HTTP MCP server exposing 65 tools across account, projects, uploads, ad image
    generation, ad copy, ad sets, UGC video, competitor research, Meta publishing and Meta analytics. Authorization is OAuth
    2.1 with dynamic client registration and PKCE S256 (scopes mcp:read, mcp:write, mcp:publish, offline_access, filtered
    at tools/list) or an account API key. Listed in the official MCP registry as com.admakeai/admakeai. Works with Claude
    Code/Desktop, Cursor, VS Code/Copilot, Windsurf, Codex, Gemini CLI, and Cline.
  humanURL: https://admakeai.com/agents
  baseURL: https://admakeai.com/api/mcp
  tags:
  - Advertising
  - Marketing
  - AdTech
  - Generative AI
  - Image Generation
  - Video Generation
  - Meta Ads
  - Competitive Intelligence
  - MCP
  - Agents
  - Agent Skills
  properties:
  - type: MCPServer
    url: https://admakeai.com/api/mcp
  - type: MCPServer
    url: mcp/admakeai-mcp.yml
  - type: ToolCrosswalk
    url: mcp/admakeai-tool-crosswalk.yml
  - type: AgenticAccess
    url: agentic-access/admakeai-agentic-access.yml
  - type: OAuthScopes
    url: scopes/admakeai-scopes.yml
  - type: Documentation
    url: https://admakeai.com/agents
- name: AdMakeAI Agent Skill
  description: Published SKILL.md that teaches an agent tool selection from natural-language intent, credit mechanics, pagination,
    destructive-action confirmation, and prompt patterns for ad creative. Installed via 'npx skills add admakeai/agent-skills'
    — note that command resolves to a GitHub org that does not exist; the repository is at github.com/mesmerlord/admakeai-agent-skills.
  humanURL: https://admakeai.com/agents
  baseURL: https://admakeai.com/agents
  tags:
  - Advertising
  - Marketing
  - AdTech
  - Generative AI
  - Image Generation
  - Video Generation
  - Meta Ads
  - Competitive Intelligence
  - MCP
  - Agents
  - Agent Skills
  properties:
  - type: AgentSkill
    url: https://admakeai.com/agents
  - type: AgentSkill
    url: skills/_index.yml
  - type: SourceCode
    url: https://github.com/mesmerlord/admakeai-agent-skills
common:
- type: WellKnown
  url: well-known/admakeai-well-known.yml
- type: LLMsTxt
  url: llms/admakeai-llms.txt
- type: Packages
  url: packages/admakeai-packages.yml
- type: Authentication
  url: authentication/admakeai-authentication.yml
- type: OAuthScopes
  url: scopes/admakeai-scopes.yml
- type: AgenticAccess
  url: agentic-access/admakeai-agentic-access.yml
- type: AgentSkill
  url: skills/_index.yml
- type: Conventions
  url: conventions/admakeai-conventions.yml
- type: ErrorCatalog
  url: errors/admakeai-error-codes.yml
- type: Conformance
  url: conformance/admakeai-conformance.yml
- type: Lifecycle
  url: lifecycle/admakeai-lifecycle.yml
- type: DataModel
  url: data-model/admakeai-data-model.yml
- type: Plans
  url: plans/admakeai-plans-pricing.yml
- type: RateLimits
  url: rate-limits/admakeai-rate-limits.yml
- type: DomainSecurity
  url: security/admakeai-domain-security.yml
- type: DeveloperPortal
  url: https://admakeai.com/agents
- type: Documentation
  url: https://admakeai.com/api/docs
- type: APIReference
  url: https://admakeai.com/api/docs
- type: GettingStarted
  url: https://admakeai.com/connect
- type: Support
  url: https://admakeai.com/resources/faq
- type: Blog
  url: https://admakeai.com/blog
- type: Pricing
  url: https://admakeai.com/pricing
- type: SignUp
  url: https://admakeai.com/register
- type: TermsOfService
  url: https://admakeai.com/resources/terms-of-service
- type: PrivacyPolicy
  url: https://admakeai.com/resources/privacy-policy
- type: SourceCode
  url: https://github.com/mesmerlord/admakeai-mcp
maintainers:
- FN: AdMakeAI
  url: https://admakeai.com/
  email: support@admakeai.com
generated:
  by: apis.io/add
  model: claude-opus-4-8
  confidence: 90
  at: '2026-08-11T12:03:43.826Z'
x-enrichment:
  date: '2026-08-11'
  status: enriched
  artifacts_added: 24
  pass: local-v1
x-coverage:
  state: covered
  note: 'The human surface of admakeai.com is unreadable to any non-browser client — every HTML path, including paths that
    do not exist, returns HTTP 403 behind a Cloudflare managed challenge, so /pricing, /api/docs, /blog, /connect and the
    declared sitemaps could not be read. The machine surface is exempted from that challenge and is unusually rich: /llms.txt,
    /.well-known/mcp.json, /.well-known/agent-skills.json and the OAuth metadata documents all returned 200, and a first-party
    65-tool manifest with input schemas was recovered from the provider''s GitHub repositories. This profile is therefore
    built entirely from machine-readable sources.'
  evidence:
  - url: https://admakeai.com/llms.txt
    status: 200
  - url: https://admakeai.com/.well-known/mcp.json
    status: 200
  - url: https://admakeai.com/.well-known/oauth-authorization-server
    status: 200
  - url: https://admakeai.com/api/docs
    status: 403
  - url: https://admakeai.com/api/mcp
    status: 403
  - url: https://github.com/admakeai/agent-skills
    status: 404
  checked: '2026-08-11'