OpenAI Ads MCP

openai-ads-mcp

Trakkr tracks the full AI-visibility funnel, organic and paid. This is the open-source paid-side companion.

openai-ads-mcp is a typed Model Context Protocol server for OpenAI Ads, ChatGPT Ads, and OpenAI's Advertiser API. It lets Claude, Cursor, Codex, VS Code, and other MCP clients inspect Ads accounts, read performance insights, build paused campaigns, upload creatives, manage audiences, and send conversion events.

People often search for this as a ChatGPT Ads MCP because the ads appear in ChatGPT. The package keeps the OpenAI Ads MCP name because ChatGPT Ads are managed through OpenAI Ads, Ads Manager, and the OpenAI Advertiser API.

Current public release: 0.1.7.

It ships in two runtimes with the same tool names, arguments, defaults, safety model, and vendored OpenAPI reference:

The goal is simple: make OpenAI Ads workable from an AI assistant without making spend easy to trigger by accident.

Install

Python with uvx:

export OPENAI_ADS_API_KEY="..."

export OPENAI_ADS_MCP_READONLY=1 uvx openai-ads-mcp

Python with pip:

python -m pip install openai-ads-mcp

export OPENAI_ADS_API_KEY="..." export OPENAI_ADS_MCP_READONLY=1 openai-ads-mcp

Node with npx:

export OPENAI_ADS_API_KEY="..."

export OPENAI_ADS_MCP_READONLY=1 npx -y openai-ads-mcp

Node with npm:

npm install -g openai-ads-mcp

export OPENAI_ADS_API_KEY="..." export OPENAI_ADS_MCP_READONLY=1 openai-ads-mcp

For local development from this monorepo:

cd services/openai-ads-mcp/python

python -m pip install -e . python -m openai_ads_mcp

cd ../typescript npm install npm run build node dist/index.js

Configuration

Create an Ads API key in OpenAI Ads Manager, then pass it as an environment variable.

export OPENAI_ADS_API_KEY="..."

Recommended first connection:

export OPENAI_ADS_MCP_READONLY=1

uvx openai-ads-mcp

Or with Node:

export OPENAI_ADS_MCP_READONLY=1

npx -y openai-ads-mcp

Readonly mode hides every write tool. They are absent from tools/list and cannot be called. Once you have confirmed the account and inspected data, unset OPENAI_ADS_MCP_READONLY to enable writes.

Optional environment variables:

Discovery Metadata

This repo includes server.json for the official MCP Registry and downstream MCP directories. The canonical registry name is:

io.github.trakkr-aisearch/openai-ads-mcp

The Node package includes the matching mcpName, and the Python package README includes the matching mcp-name marker for PyPI ownership verification.

The registry metadata also advertises the hosted read-only Streamable HTTP endpoint:

https://openai-ads-mcp.trakkr.ai/mcp

That hosted endpoint is for discovery and read-only usage. It does not store or use a Trakkr-owned OpenAI Ads API key. The hosted endpoint allows anonymous initialize and tools/list; Ads API tool calls require the caller to send X-OpenAI-Ads-API-Key.

MCP client examples

Claude Code, Python runtime

claude mcp add openai-ads \

-e OPENAI_ADS_API_KEY=your_ads_key_here \ -e OPENAI_ADS_MCP_READONLY=1 \ -- uvx openai-ads-mcp

Claude Code, Node runtime

claude mcp add openai-ads \

-e OPENAI_ADS_API_KEY=your_ads_key_here \ -e OPENAI_ADS_MCP_READONLY=1 \ -- npx -y openai-ads-mcp

Cursor or Claude Desktop

{

"mcpServers": { "openai-ads": { "command": "uvx", "args": ["openai-ads-mcp"], "env": { "OPENAI_ADS_API_KEY": "your_ads_key_here", "OPENAI_ADS_MCP_READONLY": "1" } } } }

Use "command": "npx" and "args": ["-y", "openai-ads-mcp"] for the Node runtime.

Codex CLI

[mcp_servers.openai_ads]

command = "uvx" args = ["openai-ads-mcp"] env = { OPENAI_ADS_API_KEY = "your_ads_key_here", OPENAI_ADS_MCP_READONLY = "1" }

MCP Registry

Registry-compatible clients should discover this server by name:

io.github.trakkr-aisearch/openai-ads-mcp

The registry metadata lists npm, PyPI, and the hosted Streamable HTTP endpoint. The hosted endpoint does not require an API key for discovery, but it does require X-OpenAI-Ads-API-Key for Ads API tool calls.

Docker

The repository includes production Dockerfiles for hosted Streamable HTTP deployments:

docker build -t openai-ads-mcp .

docker run --rm -p 8080:8080 \ -e OPENAI_ADS_MCP_HOSTED_PUBLIC=1 \ -e OPENAI_ADS_MCP_TELEMETRY_SALT="local-test-salt" \ openai-ads-mcp

The narrower typescript/Dockerfile is used by the Cloud Run deploy script. For local stdio use, prefer uvx openai-ads-mcp or npx -y openai-ads-mcp.

Streamable HTTP

The Node runtime can also serve MCP over Streamable HTTP for hosted or team deployments:

export OPENAI_ADS_MCP_HTTP_TOKEN="choose_a_long_random_token"

export OPENAI_ADS_MCP_READONLY=1 npx -y openai-ads-mcp --http

Defaults:

• URL: http://127.0.0.1:8080/mcp locally, or https://your-host/mcp behind a proxy.
• Health checks: GET /healthz, GET /health, and GET /ready.
• Remote mode forces OPENAI_ADS_MCP_READONLY=1 unless OPENAI_ADS_MCP_HTTP_ALLOW_WRITES=1 is set.
• OPENAI_ADS_MCP_HTTP_TOKEN protects the MCP endpoint with Authorization: Bearer .
• Clients may send X-OpenAI-Ads-API-Key per request, or the server can use a server-side OPENAI_ADS_API_KEY.

Useful hosted env vars:

For public hosted endpoints, keep writes disabled and require users to bring their own Ads API key per request. Do not put a shared Ads API key in browser-visible config.

Public hosted mode

For a public discovery endpoint, use:

export OPENAI_ADS_MCP_HOSTED_PUBLIC=1

export OPENAI_ADS_MCP_TELEMETRY_SALT="long_random_value" npx -y openai-ads-mcp --http

Hosted public mode:

• forces readonly mode
• refuses to start if OPENAI_ADS_MCP_HTTP_ALLOW_WRITES=1
• refuses to start if OPENAI_ADS_API_KEY is present
• rejects X-OpenAI-Ads-API-Base-Url
• allows anonymous initialize and tools/list
• requires X-OpenAI-Ads-API-Key for Ads API tool calls
• rate-limits discovery and tool calls
• logs only redacted summaries, hashes, counts, status, latency, and client metadata

The production runbook is in HOSTED_DEPLOY.md.

Tool Surface

The Python and Node runtimes expose the same 27 tools.

High-use tools

get_insights accepts the current tagged time-range shape, for example:

{"type":"unix_range","start":1764547200,"end":1765152000}

The older nested shape is normalized for backward compatibility.

For conversion optimization, pass bidding_type="conversions" and exactly one conversion_event_setting_ids value to create_campaign. The campaign cannot use product-feed mode, and child ad groups must bill by click. build_campaign offers the same path through its singular conversion_event_setting_id helper argument. The bid is a CPA input even though OpenAI bills the child ad group per click.

OpenAI's Bulk API remains a limited preview and is not exposed as a general MCP tool. Product-feed campaign objects are supported, but feed connection and catalog upload still happen in Ads Manager or through OpenAI's supported SFTP flow.

Safety Model

This server can affect real ad spend, so the defaults are deliberately cautious.

1. Create tools default to paused. build_campaign creates every object paused.
2. Activations are separate tools: set_campaign_state, set_ad_group_state, and set_ad_state.
3. Budget-setting paths enforce OPENAI_ADS_BUDGET_CEILING_USD, default 100.
4. To exceed the ceiling, pass confirm_budget=True.
5. OPENAI_ADS_MCP_READONLY=1 hides every write tool entirely.
6. Conversion ingest validates at most 1000 events per call, timestamps no older than 7 days, and timestamps no more than 10 minutes in the future.
7. Use validate_only=true to validate a conversion batch without ingesting it.
8. The server never logs API keys or conversion user data.

MCP annotations are set on every tool. Read tools use readOnlyHint. Write tools use readOnlyHint=false. Activation and budget-changing tools are marked destructive and open-world so hosts can prompt before running them.

Worked Example

First, connect safely:

export OPENAI_ADS_API_KEY="..."

export OPENAI_ADS_MCP_READONLY=1 uvx openai-ads-mcp

Ask your assistant:

Call get_account and list_campaigns. Confirm the Ads key works and show me what already exists.

Then restart without readonly mode and build a paused campaign:

Use draft_context_hints for "AI visibility monitoring software" aimed at growth teams with comparison intent.

Then call build_campaign with:

• name: "AI visibility category test"
• budget_usd: 50
• ad_group: name "Growth teams", billing_event "click", max_bid_usd 1.25, context_hints from the draft
• ads: two chat_card variants using my uploaded file_id

Do not activate anything.

Review the returned campaign, ad group, ads, budget, targeting, and review status. When you are ready to go live, activate each layer explicitly:

Call set_campaign_state with state="activate".

Call set_ad_group_state with state="activate". Call set_ad_state for the approved ad with state="activate".

The Organic Half

Paid placements answer: where did you buy attention?

Trakkr answers: where does your brand show up orga