AI agents call serve_ad to retrieve information from AdButler without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
ID | number | Yes | Your AdButler account ID |
ip | string | — | IPv4 address for geographic targeting (required for server-side requests) |
kw | array | — | Keywords for keyword targeting |
rf | number | — | Pass 1 to include is_redirectable field in response |
sh | number | — | Screen height for platform targeting |
sw | number | — | Screen width for platform targeting |
ua | string | — | User agent string for platform targeting |
pid | number | — | Page ID for unique delivery/roadblocks (random number, same for all zones on page) |
spr | number | — | Screen pixel ratio for platform targeting |
size | string | — | Expected ad size (e.g. "300x250") |
type | string | Yes | Response type: "json" for most eligible ad, "jsonr" for all eligible ads ranked |
place | number | — | Place counter for unique delivery (0, 1, 2, etc.) |
Parameters from the server's own tool schema.
The tool requests and returns ad delivery content for verification purposes. Although it uses POST (possibly for ad impression tracking), its stated purpose is to retrieve/verify what ad would be served, making it primarily a read/query operation. The low severity reflects that misuse would at most generate spurious ad impressions rather than cause data loss or financial harm.
From the tool's definition 'Request ad delivery for a zone. Returns the ad(s) that would be served, useful for verifying ad setup.'
Risk signalsHigh parameter count (16 properties)
Attacks that exploit this kind of access
Request ad delivery for a zone. Returns the ad(s) that would be served, useful for verifying ad setup. Uses POST /adserve. It is categorised as a Read tool in the AdButler MCP Server, which means it retrieves data without modifying state.
serve_ad accepts 12 parameters: ID, ip, kw, rf, sh, sw, ua, pid, spr, size, type, place. Required: ID, type. 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 serve_ad: 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.
serve_ad is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the serve_ad 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 serve_ad. 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.
serve_ad 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 →