AI agents use create_demand_source to create or update resources in AdButler — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AdButler environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
name | string | Yes | Demand source name |
status | string | — | Whether to send bid requests (default: active) |
network | string | Yes | Network type: 'adview', 'aerserv', 'inmobi', 'inneractive', 'loopme', 'mobilefuse', 'onebyaol', 'pubmatic', 'pubnative', 'smaato', 'startapp', 'tappx', 'consuma |
spend_limit | number | — | Spend limit amount |
spend_limit_end | string | — | Spend limit end date (ISO-8601) |
spend_limit_start | string | — | Spend limit start date (ISO-8601) |
spend_limit_period | string | — | Spend limit reset interval |
Parameters from the server's own tool schema.
Creating a new demand source is a Write operation—it adds a new entity to the AdButler system. This is reversible (can be archived or deleted later) and has no financial implications by itself. Severity is medium because misconfiguration of demand sources could affect ad delivery campaigns and revenue reporting, but the damage is limited to the newly created entity and is easily remediated.
From the tool's definition Tool name 'create_demand_source' and description 'Create a new demand source' indicate data creation. Related tools like 'archive_advertiser', 'archive_campaign', and 'bulk_upload_add_data_list' confirm this server handles reversible data modifications within…
Attacks that exploit this kind of access
Create a new demand source. It is categorised as a Write tool in the AdButler MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
create_demand_source accepts 7 parameters: name, status, network, spend_limit, spend_limit_end, spend_limit_start, spend_limit_period. Required: name, network. The full parameter table on this page comes from the server's own tool schema.
Register the AdButler MCP server in PolicyLayer and add a rule for create_demand_source: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches AdButler. Nothing to install.
create_demand_source is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_demand_source rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for create_demand_source. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
create_demand_source is provided by the AdButler MCP server (adbutler/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →