OpenAI Ads MCP server
by danielgtmn
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Bind address. | 0.0.0.0 |
| PORT | No | Listen port. | 8000 |
| LOG_LEVEL | No | DEBUG, INFO, WARNING, ERROR, or CRITICAL. HTTP client header logs stay off. | INFO |
| ADS_MAX_PAGES | No | Maximum pages followed when fetch_all is true. | 25 |
| MCP_READ_ONLY | No | Write tools are registered only when this is false. Any other or missing value is read-only. | true |
| MCP_AUTH_TOKEN | Yes | Bearer token required on /mcp. Never logged. | |
| ADS_MAX_RETRIES | No | Extra attempts after HTTP 429. | 5 |
| OPENAI_ADS_API_KEY | Yes | Ads API bearer token. Never logged. | |
| OPENAI_ADS_BASE_URL | No | Advertiser API origin. Override only for tests. | https://api.ads.openai.com/v1 |
| ADS_GLOBAL_RATE_LIMIT | No | Requests per minute across endpoints, per process. | 1200 |
| ADS_RETRY_MAX_SECONDS | No | Cap for a single retry wait. | 30 |
| ADS_RETRY_BASE_SECONDS | No | Exponential backoff base when Retry-After is absent. | 1 |
| ADS_ENDPOINT_RATE_LIMIT | No | Requests per minute for one endpoint, per process. | 600 |
| ADS_RATE_WINDOW_SECONDS | No | Window for those limits. | 60 |
| ADS_REQUEST_TIMEOUT_SECONDS | No | HTTP timeout. | 30 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityNo data
ResponsivenessNo issues