OpenAI Ads MCP server
io.github.trakkr-aisearch/openai-ads-mcptrakkr-aisearchstreamable-httpv0.1.7Scanned
OpenAI Ads MCP for ChatGPT Ads campaigns, creatives, audiences, insights, and conversions.
13 tools: 2 change things and 11 only read.
- Reads private data · 0
- Reads text others write · 12
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
2 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the OpenAI Ads MCP server can do
The OpenAI Ads MCP server is published by the GitHub account trakkr-aisearch. It has 13 tools. It can create or change data (2 tools: manage_conversions and draft_context_hints), but cannot delete data. 11 tools only read.
12 tools bring in text other people can write (get_account, list_campaigns, get_campaign and 9 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 0.1.7.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
13 tools
Changes things 2Claude Code: ask
draft_context_hintsDraft deterministic context_hints for an ad group from product, audience, intent, and keywords.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Draft deterministic context_hints for an ad group from product, audience, intent, and keywords.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
manage_conversionsManage conversion pixels, API keys, event settings, and conversion reporting.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Manage conversion pixels, API keys, event settings, and conversion reporting.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 11Show 11 read-only tools
get_accountGet the authenticated OpenAI Ads account.Reads text others writeNo findings
Why it is in this group
- The name "get_account" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get the authenticated OpenAI Ads account. Use this first to verify that OPENAI_ADS_API_KEY works and to read account id, name, timezone, currency, and settings.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_adGet one ad by id, including review_status and creative metadata.Reads text others writeNo findings
Why it is in this group
- The name "get_ad" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "get" and "review": it reads comments, which other people can write.
Description, as the server wrote it Get one ad by id, including review_status and creative metadata.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_ad_groupGet one ad group by id.Reads text others writeNo findings
Why it is in this group
- The name "get_ad_group" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get one ad group by id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_audienceGet one custom audience by id.Reads text others writeNo findings
Why it is in this group
- The name "get_audience" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get one custom audience by id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_campaignGet one campaign by id.Reads text others writeNo findings
Why it is in this group
- The name "get_campaign" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get one campaign by id.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_insightsGet performance insights for account, campaign, ad group, or ad scope.Reads text others writeNo findings
Why it is in this group
- The name "get_insights" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Get performance insights for account, campaign, ad group, or ad scope. Supports fields, filters, sort, product/country/device segments, time ranges, and cursor pagination.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_ad_groupsList ad groups for a campaign.Reads text others writeNo findings
Why it is in this group
- The name "list_ad_groups" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List ad groups for a campaign.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_adsList ads in an ad group.Reads text others writeNo findings
Why it is in this group
- The name "list_ads" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List ads in an ad group.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_audiencesList custom audiences for the authenticated ad account.Reads text others writeNo findings
Why it is in this group
- The name "list_audiences" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List custom audiences for the authenticated ad account.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
list_campaignsList campaigns in the authenticated ad account with cursor pagination.Reads text others writeNo findings
Why it is in this group
- The name "list_campaigns" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it List campaigns in the authenticated ad account with cursor pagination.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
search_geoSearch geo targets for targeting.locations.include and return ids usable in campaign targeting.Reads text others writeNo findings
Why it is in this group
- The name "search_geo" says "search": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Search geo targets for targeting.locations.include and return ids usable in campaign targeting.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write12
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:12 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 2
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://openai-ads-mcp.trakkr.ai/mcp: tools/list returned 13 tools to an anonymous client, including manage_conversions (write), draft_context_hints (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.1.7. Values in angle brackets are yours to fill in.
claude mcp add --transport http openai-ads https://openai-ads-mcp.trakkr.ai/mcpclaude mcp add --transport http openai-ads https://openai-ads-mcp.trakkr.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__openai-ads__get_account",
"mcp__openai-ads__list_campaigns",
"mcp__openai-ads__get_campaign",
"mcp__openai-ads__list_ad_groups",
"mcp__openai-ads__get_ad_group",
"mcp__openai-ads__list_ads",
"mcp__openai-ads__get_ad",
"mcp__openai-ads__get_insights",
"mcp__openai-ads__list_audiences",
"mcp__openai-ads__get_audience",
"mcp__openai-ads__search_geo"
],
"ask": [
"mcp__openai-ads__manage_conversions",
"mcp__openai-ads__draft_context_hints"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as openai-ads. Review it before you use it.
Capability tags behind 12 rules
- mcp__openai-ads__get_account untrusted-input
- mcp__openai-ads__list_campaigns untrusted-input
- mcp__openai-ads__get_campaign untrusted-input
- mcp__openai-ads__list_ad_groups untrusted-input
- mcp__openai-ads__get_ad_group untrusted-input
- mcp__openai-ads__list_ads untrusted-input
- mcp__openai-ads__get_ad untrusted-input
- mcp__openai-ads__get_insights untrusted-input
- mcp__openai-ads__list_audiences untrusted-input
- mcp__openai-ads__get_audience untrusted-input
- mcp__openai-ads__search_geo untrusted-input
- mcp__openai-ads__manage_conversions untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.trakkr-aisearch/openai-ads-mcp/verify?hash=e49d1335722a0ceba3e39e220d04267966ac6678f7d4076e3c73b6d55cecc3c8" | jq -e '.changed == false'Pinned hash e49d1335722a, from Nov 20, 2026, 16:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.trakkr-aisearch/openai-ads-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.trakkr-aisearch/openai-ads-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:50 UTC.
OpenAI Ads MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the OpenAI Ads MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 2 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the OpenAI Ads MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the OpenAI Ads MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the OpenAI Ads MCP server have?
- 13 tools: 2 write, 11 read. manage_conversions, draft_context_hints, get_account, list_campaigns, get_campaign, list_ad_groups, get_ad_group, list_ads and 5 more.
Does the OpenAI Ads MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the OpenAI Ads MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the OpenAI Ads MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.