ChatGPT Ads MCP server
Related Servers
Alternatives to ChatGPT Ads MCP server
No user-submitted related servers found.
Related Servers
- AlicenseBqualityCmaintenanceEnables managing ChatGPT Advertiser campaigns from MCP-capable agents, including campaign creation, creative uploads, audience management, conversions setup, and insights retrieval.8924 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables management of OpenAI Ads campaigns, ad groups, ads, and insights through MCP, with approval-gated live mutations for safe write operations.52 npmMIT
- AlicenseBqualityCmaintenanceEnables AI assistants to read a ChatGPT Ads account — account summaries, performance insights, campaigns, ad groups, ads, product feeds and conversion setup — and, when writes are explicitly enabled, create or update campaigns, budgets and creatives with dry-run previews and before/after diffs.151MIT
- AlicenseBqualityDmaintenanceTyped MCP server for OpenAI Ads and ChatGPT Ads via the Advertiser API. Supports account, campaign, ad group, ad, creative, audience, insight, and conversion tools with readonly mode and guarded writes.123MIT
- AlicenseBqualityBmaintenanceEnables MCP clients to read Snapchat Ads campaigns and performance and to prepare preview-first changes for selected ad accounts, with opt-in write tools and explicit confirmation before applying updates.210Apache 2.0
- FlicenseNot gradedqualityCmaintenanceEnables management of Google Ads accounts via MCP, providing read and write tools for campaigns, ad groups, keywords, assets, and more, with support for reporting and mutations.-
TDQS
Scored across 30 tools
Each tool targets a distinct resource or report (campaigns vs ad groups vs ads vs feeds vs audiences vs bulk jobs), and the insights vs conversion_insights split is explicitly documented. The main friction is the large set of near-neighbor tools (get_custom_audiences / get_custom_audience / get_audience_operations / get_audience_operation, and get_write_schema / get_write_context / get_mutation) where an agent must read carefully, plus get_* names that sometimes list and sometimes read one entity.
All names share the openai_ads_ prefix and a verb_noun shape, so the set is predictable. However the verb usage is loose: get_ is used for both list operations (get_campaigns, get_ads, get_feeds) and single-entity reads, while list_ and search_ appear only once each, which weakens the pattern's signal.
30 tools is heavy for a single MCP server and sits above the comfortable 15-tool band, even though the domain (campaigns, creatives, conversions, feeds, audiences, audit, bulk) is genuinely broad. Several read-only sub-resources (audience operations, feed uploads, feed settings, landing page crawl) could reasonably be folded into parent tools to slim the surface.
Read coverage is deep and coherent across the ad lifecycle, including diagnostics and bulk job result inspection. But the surface is read-heavy: get_write_schema, get_write_context and get_mutation reference write previews and receipts while no tool actually submits a mutation, leaving a dangling step in the advertised lifecycle and no create/update/delete operations.