Skip to main content
Glama
Sign In

OpenAI Ads MCP by InsightfulPipe

by com.insightfulpipe
OverviewDiscussionsAdmin

Server Details

Hosted OpenAI Ads MCP server for Claude, ChatGPT and Cursor, with each action switched per account.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
Insightful-Pipe/openai-ads-mcp-server
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

A4.1/5.0

Scored across 4 tools

Disambiguation4/5

The four tools have mostly distinct roles: query_contexts for planning/metadata, query_data for reads, execute_action for writes, and prompts_menu for prompt catalog access. The main risk is that execute_action and query_data share nearly identical workflow language and both are labeled as the final step, while query_contexts and query_data have similar names, but the descriptions still clarify read vs write vs planning.

Naming Consistency4/5

All names use snake_case and three follow a clear verb_noun pattern: execute_action, query_contexts, query_data. prompts_menu is the minor deviation, using noun_noun rather than a verb like browse_prompts, but the set remains predictable overall.

Tool Count5/5

Four tools is well-scoped for a specialized ads workflow: two planning/context helpers and two terminal read/write operations. Each tool has a clear role and the count avoids redundancy or fragmentation.

Completeness4/5

The surface covers the core lifecycle through query_contexts for metadata, query_data for reads, execute_action for available write actions, and prompts_menu for prompt discovery. Minor gaps exist around prompt management beyond browsing and lack of a dedicated action-listing tool, but available_actions in query_contexts mitigates this.

Available Tools

4 tools
execute_actionOpenAI Ads Execute ActionA
Destructive
Inspect

Execute OpenAI Ads action (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, ad_account_id AND available_actions

  2. request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions

IMPORTANT: Always call step 2 to see the exact body structure before executing.

Rely on info from steps 1-2 to construct the action body. Follow the schema exactly.

Inputs: body (required). Returns: object

prompts_menuOpenAI Ads PromptsA
Read-only
Inspect

Browse the OpenAI Ads prompt catalog.

  1. request='menu' – List public/system prompts (optionally pass workspace_id + prompt_type).

  2. request='prompt_details' – Fetch prompt body by prompt_id. Set is_custom=True + workspace_id for workspace prompts.

Inputs: request (required), is_custom, prompt_id, prompt_type, +1 more. Returns: object

query_contextsOpenAI Ads Setup HelperA
Read-only
Inspect

Helper for planning InsightfulPipe OpenAI Ads queries and write actions.

Step 1: request='accounts' – Retrieve workspace_id, brand_id, ad_account_id, other source metadata, AND available_actions (all tables/actions you can query or execute).

Step 2: request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] – REQUIRED before querying. Replace with actions from available_actions to get the exact request body, required identifiers, fields, time ranges, and notes for each action.

Optional: request='available_actions' – Standalone call to list all available tables/actions (already included in accounts response).

Optional: request='brands' with brand_id + workspace_id to pull brand guidelines.

Inputs: request (required), actions, brand_id, platform, +1 more. Returns: object

query_dataOpenAI Ads Data QueryA
Read-only
Inspect

Query OpenAI Ads data (Step 3 (FINAL) of workflow).

REQUIRED: Complete these steps first using query_contexts:

  1. request='accounts' - Get workspace_id, brand_id, ad_account_id AND available_actions

  2. request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] - Get detailed body structure for specific action(s) using actions from available_actions

IMPORTANT: Always call step 2 to see the exact body structure before querying.

Rely on info from steps 1-2 to construct the query body. Follow the schema exactly.

Inputs: body (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    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