ENDPOINT 1
https://openai-ads-mcp.trakkr.ai/mcp
MCP server metadata
- Name
- OpenAI Ads
- Version
- 0.1.7
Typed MCP tools for OpenAI's Advertiser API. Use get_account first to confirm the API key works, then read insights before changing spend. The safest workflow is: check the account, inspect campaigns and insights, build new campaigns paused, review the created campaign, ad group, and ads, then activate each layer explicitly when the user asks. Safety model: 1. Create tools default to paused. build_campaign creates every object paused. 2. Budget-setting tools enforce OPENAI_ADS_BUDGET_CEILING_USD, default 100 USD, unless confirm_budget=True. 3. Set OPENAI_ADS_MCP_READONLY=1 for first connection. In readonly mode write actions are hidden, while conversion read actions remain available. 4. Conversion event ingestion never logs user data. Validate batches before sending them. Paid presence is half the picture. Track how your brand shows up organically across ChatGPT, Perplexity, Gemini and Claude at trakkr.ai.
Known tools 13
list_campaignsList campaigns in the authenticated ad account with cursor pagination.
Inferred read-onlyget_insightsGet performance insights for account, campaign, ad group, or ad scope.
Inferred read-onlysearch_geoSearch geo targets for targeting.locations.include and return ids usable in campaign targeting.
Inferred read-onlymanage_conversionsManage conversion pixels, API keys, event settings, and conversion reporting.
Inferred read-onlydraft_context_hintsDraft deterministic context_hints for an ad group from product, audience, intent, and keywords.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.openai-ads]
url = "https://openai-ads-mcp.trakkr.ai/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"openai-ads": {
"type": "http",
"url": "https://openai-ads-mcp.trakkr.ai/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: openai-ads
Remote MCP URL: https://openai-ads-mcp.trakkr.ai/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"openai-ads": {
"url": "https://openai-ads-mcp.trakkr.ai/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"openai-ads": {
"type": "http",
"url": "https://openai-ads-mcp.trakkr.ai/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "openai-ads",
"transport": "streamable-http",
"url": "https://openai-ads-mcp.trakkr.ai/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
ENDPOINT 2
https://api.trakkr.ai/public/mcp
MCP server metadata
- Name
- Trakkr Public Knowledge
- Version
- 1.28.1
You are Trakkr's public Knowledge MCP. Use search before fetch. Cite the Trakkr URL returned by fetch when answering. This server only exposes public marketing, research, documentation and public dataset metadata. If a user asks for private brand data, reports, prompts, citations, competitors, actions or account-specific analysis, explain that this public MCP cannot access accounts and point them to the authenticated Trakkr MCP at https://api.trakkr.ai/mcp.
Known tools 4
get_public_datasetReturn metadata and download URLs for a whitelisted public Trakkr dataset.
Inferred read-onlyget_authenticated_mcp_setupExplain when and how to connect the paid authenticated Trakkr MCP.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.trakkr-public-knowledge]
url = "https://api.trakkr.ai/public/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"trakkr-public-knowledge": {
"type": "http",
"url": "https://api.trakkr.ai/public/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: trakkr-public-knowledge
Remote MCP URL: https://api.trakkr.ai/public/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"trakkr-public-knowledge": {
"url": "https://api.trakkr.ai/public/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"trakkr-public-knowledge": {
"type": "http",
"url": "https://api.trakkr.ai/public/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "trakkr-public-knowledge",
"transport": "streamable-http",
"url": "https://api.trakkr.ai/public/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
ENDPOINT 3
https://api.trakkr.ai/mcp
Known tools 0
No tool metadata was available in the registry cache.
CONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.trakkr-ai]
url = "https://api.trakkr.ai/mcp"
enabled = true
bearer_token_env_var = "MCP_BEARER_TOKEN"
Authentication is required. Replace the placeholder locally and never commit a secret.
Claude Code
.mcp.json
{
"mcpServers": {
"trakkr-ai": {
"type": "http",
"url": "https://api.trakkr.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_BEARER_TOKEN"
}
}
}
}
Authentication is required. Replace the placeholder locally and never commit a secret.
Claude Desktop
Settings → Connectors → Add custom connector
Name: trakkr-ai
Remote MCP URL: https://api.trakkr.ai/mcp
Add the URL as a custom connector, then complete its supported authorization flow. Claude Desktop remote connectors are configured in the UI.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"trakkr-ai": {
"url": "https://api.trakkr.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_BEARER_TOKEN"
}
}
}
}
Authentication is required. Replace the placeholder locally and never commit a secret.
Visual Studio Code
.vscode/mcp.json
{
"servers": {
"trakkr-ai": {
"type": "http",
"url": "https://api.trakkr.ai/mcp",
"headers": {
"Authorization": "Bearer ${input:mcp-token}"
}
}
},
"inputs": [
{
"type": "promptString",
"id": "mcp-token",
"description": "trakkr-ai bearer token",
"password": true
}
]
}
Authentication is required. Replace the placeholder locally and never commit a secret.
Generic MCP
Client-specific MCP configuration
{
"name": "trakkr-ai",
"transport": "streamable-http",
"url": "https://api.trakkr.ai/mcp",
"headers": {
"Authorization": "Bearer YOUR_BEARER_TOKEN"
}
}
Authentication is required. Replace the placeholder locally and never commit a secret.
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.