AdsMCP
The ad monetization MCP server for AI applications.
AdsMCP is Adgentek's hosted Model Context Protocol server that enables AI agents and conversational interfaces to serve contextually relevant ads automatically — based on conversation context, user intent, and placement opportunity.
Built on a full ad server stack. Bring live demand from Adgentek, bring your own direct-sold campaigns, or both. No ad tech expertise required.
Before You Start
You need an Adgentek publisher account, an API key, and at least one active AI Surface before ads will serve.
Create your publisher account →
Setup checklist
- Create your account at app.adgentek.ai/publishers/auth
- Create an AI Surface — in the publisher dashboard, go to Inventory → Surfaces and add at least one surface (e.g.
conversational,search,voice). A surface defines where ads can appear and sets your floor eCPM. - Generate an API key — in the publisher dashboard, go to Settings → API Keys and create a key (prefixed
adgt_). This key authenticates all MCP requests.
Your account is considered Active once at least one surface is enabled.
Connect
{
"mcpServers": {
"adgentek-ads": {
"url": "https://mcp.adgentek.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY_HERE"
}
}
}
}
This is the only configuration needed. All MCP-compatible clients support this URL + Headers pattern — no local packages or environment variables required.
Platform-Specific Configuration
The connection config is identical across platforms. Only the file location and wrapper key differ.
// ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
// %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"adgentek-ads": {
"url": "https://mcp.adgentek.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY_HERE"
}
}
}
}
// ~/.claude/settings.json
{
"mcpServers": {
"adgentek-ads": {
"url": "https://mcp.adgentek.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY_HERE"
}
}
}
}
// .cursor/mcp.json
{
"mcpServers": {
"adgentek-ads": {
"url": "https://mcp.adgentek.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY_HERE"
}
}
}
}
// .vscode/mcp.json
{
"servers": {
"adgentek-ads": {
"url": "https://mcp.adgentek.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY_HERE"
}
}
}
}
{
"mcpServers": {
"adgentek-ads": {
"url": "https://mcp.adgentek.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY_HERE"
}
}
}
}
Available Tools
ads.serve
Serves a contextual ad based on the current conversation. Returns the highest-yield ad available for the given context, or null if no ad matched.
Required parameters: conversationId, userKey, surface
Optional parameters: messages, intent, sentiment, depth, language, geo, preferHtml, extras
const result = await callTool('ads.serve', {
conversationId: 'conv_abc123',
userKey: 'user_456',
surface: 'conversational',
messages: [
{ role: "user", content: "What CRM works best for a small sales team?" },
{ role: "assistant", content: "For small teams, a few options stand out..." },
{ role: "user", content: "Which ones integrate with Google Workspace?" }
],
intent: 'research',
sentiment: 65,
depth: 3,
language: 'en',
geo: 'US'
});
if (result.ad) {
displayAd(result.ad.render.markdown);
// Impressions: embed ad.impression_url as a 1x1 pixel in the browser
// Clicks: use ad.click_url as the CTA link href
}
Surface types: conversational, search, voice, creative, web
Intent values: purchase, research, support, informational
ads.prefetch
Batch-request up to 10 ad contexts in a single call. Each item in the batch uses the same parameters as ads.serve.
Required: batch (array, max 10 items — each requiring conversationId, userKey, surface)
const results = await callTool('ads.prefetch', {
batch: [
{ conversationId: 'conv_1', userKey: 'user_456', surface: 'conversational', messages: [...] },
{ conversationId: 'conv_2', userKey: 'user_456', surface: 'search', messages: [...] }
]
});
// results.ads — array of ad objects (null where no ad matched)
// results.prefetched_count — number of ads returned
// results.truncated — true if your batch exceeded the 10-item limit
Ad Response Format
When ads.serve returns a matched ad:
{
"ad": {
"id": "ad_abc123",
"title": "Product Title",
"content": "Description text",
"cta": "Learn More",
"click_url": "https://api.adgentek.ai/.../click?...",
"impression_url": "https://api.adgentek.ai/.../pixel.gif?...",
"render": {
"markdown": "## Title\n\nContent\n\n[CTA](click_url)",
"plain": "Title - Content - CTA",
"html": "<div>...</div>"
}
},
"targeting_scores": { ... }
}
When no ad matched:
{
"ad": null,
"reason": "no_eligible_ads",
"targeting_scores": { ... }
}
Tracking
Impression and click tracking is handled via the URLs provided in every ad response. These work in any rendering context — browser, in-app webview, or embedded UI.
- Impressions: Load
ad.impression_urlas a 1×1 pixel image when the ad is displayed - Clicks: Use
ad.click_urlas the CTA link href (signed redirect to advertiser destination)
<img src="{ad.impression_url}" width="1" height="1" style="display:none" alt="" />
<a href="{ad.click_url}" target="_blank" rel="noopener noreferrer">{ad.cta}</a>
Do not modify or bypass these URLs — they are signed and time-limited.
MCP Resources
The server exposes read-only documentation as MCP resources:
Full Ad Server — Bring Your Own Ads
AdsMCP is not a demand source with an MCP interface bolted on. It is a full ad server.
Publishers can:
- Use Adgentek's live demand — we have established relationships across programmatic, performance, and direct demand channels, with more being added continuously
- Bring your own campaigns — upload direct-sold advertiser deals and serve them through the same
ads.servecall - Layer in additional ad sources — connect your own demand partners alongside Adgentek's, with automatic yield optimization across all of them
Your inventory. Your demand relationships. One unified server.
Privacy Architecture
User conversations are private. Raw conversation content is never shared with advertisers, demand partners, or third parties.
AdsMCP transmits only derived signals to ad buyers — the minimum information required to match a relevant ad:
Go Live
- Create your publisher account and generate an API key
- Create at least one AI Surface in the publisher dashboard (Inventory → Surfaces)
- Add the MCP config to your AI application using the connection snippet above
- Contact [email protected] to verify your integration and activate live demand
About Adgentek
AdsMCP is built and operated by Adgentek.
Adgentek exists because AI apps are a fundamentally different kind of publisher — and they deserve ad infrastructure built for them, not retrofitted from the display web. Conversational interfaces have richer intent signals, longer engagement sessions, and none of the legacy constraints that shaped how traditional ad tech was built.
Adgentek builds the ad monetization layer that is native to this environment: context-aware, privacy-safe, MCP-native, and designed to serve AI apps of any size — from a single-developer GPT to a multi-surface conversational platform. Our demand relationships span programmatic, direct, and performance channels, and publishers can layer in their own ad sources alongside ours.
If you are building an AI app and want ad revenue without building ad infrastructure, AdsMCP is what you are looking for.