Openai MCP Server

Read-only MCP server for the OpenAI Ads API: campaigns, ad groups, ads, and insights.

Remote serverstreamable-http

What is the Openai MCP server?

Openai MCP server exists for a simple reason — assistants are far more useful when they can act on Openai directly instead of describing what you should do. Read-only MCP server for the OpenAI Ads API: campaigns, ad groups, ads, and insights.

What you get

A Model Context Protocol (MCP) server for the OpenAI Ads (Advertiser) API. It lets MCP-compatible clients — Claude Desktop, Cursor, VS Code, and others — read your OpenAI Ads campaigns, ad groups, ads, and performance insights through natural language.

The OpenAI Ads API exposes an advertiser's account, campaigns, ad groups, ads, and reporting. This server wraps the read endpoints of that API as MCP tools so an AI assistant can answer questions like:

  • 11 read-only tools — covering the account, campaigns, ad groups, ads, and insights at every level
  • Faithful responses — — the API's JSON is returned as-is, so nothing is lost in translation
  • Clear errors — — HTTP status and the API error body are surfaced to the model instead of being swallowed
  • Micros-aware — — every tool description explains the micros convention so the assistant can present human-readable currency
  • Cursor pagination — passthrough (limit, order, after, before)
  • Zero-install — via npx — npx -y @hypd-ai/openai-ads-mcp, no clone or build

What the assistant can call

Once Openai is connected, these are the calls the assistant has available:

  • get_ad_account — Fetch the ad account for the configured key. Great as a connectivity check
  • list_campaigns — List campaigns (objective, budget, country targeting)
  • get_campaign — Fetch a single campaign by ID
  • list_ad_groups — List ad groups, optionally filtered by campaign
  • get_ad_group — Fetch a single ad group by ID (bidding config, context hints)
  • list_ads — List ads, optionally filtered by ad group
  • get_ad — Fetch a single ad by ID (creative + review status)
  • get_account_insights — Performance insights for the whole account
  • get_campaign_insights — Performance insights for one campaign
  • get_ad_group_insights — Performance insights for one ad group
  • get_ad_insights — Performance insights for one ad
  • Cursor — The Cursor tool exposed by this server

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration and credentials

You will need 2 environment variables: OPENAI_ADS_API_KEY, OPENAI_ADS_BASE_URL. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Openai's toolset — get_ad_account, list_campaigns, get_campaign and 9 more — is a fair guide to whether it matches your workflow. It is maintained by HYPD-AI; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Openai.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the openai mcp server does with a few real requests.

Available tools

ToolWhat it does
get_ad_accountFetch the ad account for the configured key. Great as a connectivity check.
list_campaignsList campaigns (objective, budget, country targeting).
get_campaignFetch a single campaign by ID.
list_ad_groupsList ad groups, optionally filtered by campaign.
get_ad_groupFetch a single ad group by ID (bidding config, context hints).
list_adsList ads, optionally filtered by ad group.
get_adFetch a single ad by ID (creative + review status).
get_account_insightsPerformance insights for the whole account.
get_campaign_insightsPerformance insights for one campaign.
get_ad_group_insightsPerformance insights for one ad group.
get_ad_insightsPerformance insights for one ad.
CursorThe Cursor tool exposed by this server.

How to install the Openai MCP server

{
  "mcpServers": {
    "openai-ads": {
      "command": "npx",
      "args": ["-y", "@hypd-ai/openai-ads-mcp"],
      "env": {
        "OPENAI_ADS_API_KEY": "your-openai-ads-api-key"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
OPENAI_ADS_API_KEYCredential the server authenticates with.Yes
OPENAI_ADS_BASE_URLEndpoint or connection string the server talks to.Yes

Example prompts to try

  • Use Openai to get ad account.
  • Use Openai to list campaigns.
  • Use Openai to get campaign.

Frequently asked questions

It connects Openai to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (get_ad_account, list_campaigns, get_campaign, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Openai directly.