Skip to main content
Glama

Ads MCP

by io.github.adkit
OverviewDiscussionsAdmin

adkit_library

Browse 500k+ ads from over 1000 advertisers across Meta, Google, and LinkedIn, track advertisers, and save selected ads to shareable inspiration boards. For advertiser list/search, params.scope is library (default, all advertisers) or watchlist (the selected project's My Watchlist). Create and fill boards before setting shareEnabled: true through boards update, and only enable sharing when the user explicitly asks. The user's own campaigns live in adkit_manage.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoEntity identifier. Required for get, track, untrack, boards get, boards update, and boards add-ads.
actionYesLibrary action to execute. For advertisers, track/untrack changes the selected project watchlist. For boards, list/get reads the selected project, create/update changes board metadata, and add-ads saves selected library ads.
entityYesLibrary entity to query.
paramsNoFree-form request params. Sent as query for GET requests and as body fields for mutations.
projectIdNoRequired. Get from adkit_projects. Auto-resolves only for single-project users.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"Library action to execute. For advertisers, track/untrack changes the selected project watchlist. For boards, create/update changes board metadata and add-ads saves selected library ads."New value: +"Library action to execute. For advertisers, track/untrack changes the selected project watchlist. For boards, list/get reads the selected project, create/update changes board metadata, and add-ads saves selected library ads."
    • changedInput schema / properties / id / description
      Previous value: -"Entity identifier. Required for get, track, untrack, boards update, and boards add-ads."New value: +"Entity identifier. Required for get, track, untrack, boards get, boards update, and boards add-ads."
  2. Changed4 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"Library action to execute. For advertisers, track/untrack adds/removes an existing advertiser from the selected project watchlist; add requires a website or ad library URL and tracks the advertiser. For a name, search first, then track its ID."New value: +"Library action to execute. For advertisers, track/untrack changes the selected project watchlist. For boards, create/update changes board metadata and add-ads saves selected library ads."
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "list",
-  "search",
-  "get",
-  "similar",
-  "add",
-  "track",
-  "untrack"
-]New value: +[
+  "list",
+  "search",
+  "get",
+  "similar",
+  "add",
+  "track",
+  "untrack",
+  "create",
+  "update",
+  "add-ads"
+]
    • changedInput schema / properties / entity / enum
      Previous value: -[
-  "advertisers",
-  "ads"
-]New value: +[
+  "advertisers",
+  "ads",
+  "boards"
+]
    • changedInput schema / properties / id / description
      Previous value: -"Entity identifier. Required for get, track, and untrack; track/untrack change watchlist membership for the selected project only."New value: +"Entity identifier. Required for get, track, untrack, boards update, and boards add-ads."
  3. First observed

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are sparse (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false), so the description carries the burden. It discloses side effects like track/untrack changing the watchlist and boards update/creation altering metadata. It also mentions the safety rule about sharing. No contradiction with annotations. Lacks explicit detail on reversibility or exact consequences, but is nonetheless transparent enough for most agent use cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but well-structured. It opens with the core purpose, then adds critical scoping and safety constraints, and ends with a pointer to a sibling tool. Every sentence adds necessary information; there is no fluff or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multiple entities, actions, and a free-form params object), the description covers almost everything an agent needs: scope semantics, projectId requirement, board sharing safety, and differentiation from adkit_manage. No output schema is present, but the description doesn't overpromise return details. The only minor omission is explicit pagination/return format, but that is not essential for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (all params have descriptions), so baseline is 3. The description adds extra value by clarifying the semantics of params.scope for library vs watchlist, and specifying which actions apply to which entities and when id/projectId are required. This goes beyond schema descriptions and helps the agent construct correct calls.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific purpose: browse ads across platforms, track advertisers, and save ads to boards. It clearly distinguishes from sibling adkit_manage by noting the user's own campaigns live there. This differentiates it from other tools without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit usage context: explains the scope parameter (library vs watchlist), instructs when to enable sharing (only when the user explicitly asks), and directs users to adkit_manage for their own campaigns. This gives clear when-to-use and when-not-to-use guidance, going beyond basic function description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ads MCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources