OpenAI and ChatGPT Ads tools for campaigns, creatives, audiences, and insights.
AI & Agentsv0.1.6streamable-httpopenai-ads-mcp.trakkr.ai repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 2776ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo OpenAI Ads@0.1.6 |
| tooling | 33 / 35 | tools/list OK: 12 tools e.g. "get_account"; 12/12 described, 10/12 fully-typed schemas, median description 64 chars |
| latency | 4 / 10 | initialize round-trip 2776ms |
| provenance | 15 / 15 | description present; repository linked; version 0.1.6; namespace io.github.trakkr-aisearch matches endpoint/repo |
Score 92/100 · latency 2776ms · 12 tools · protocol access: open ⓘ
Security, data integrity, citation quality, and advertised claims are measured separately from protocol uptime. Missing evidence is marked unverified, never converted into a pass.
No deterministic trust observations published yet. This means unaudited—not safe, unsafe, accurate, or inaccurate.
Machine-readable receipt: /api/trust/io.github.trakkr-aisearch/openai-ads-mcp.json
Claude Code:
claude mcp add --transport http openai-ads-mcp https://openai-ads-mcp.trakkr.ai/mcp
Generic MCP client config:
{ "mcpServers": { "openai-ads-mcp": { "type": "http", "url": "https://openai-ads-mcp.trakkr.ai/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/io.github.trakkr-aisearch/openai-ads-mcp · referral link https://mcpqueen.com/go/io.github.trakkr-aisearch/openai-ads-mcp (counts as “routed via the queen”).
Live operational-grade badge, re-probed continuously — not a security or data-quality certification. Put it in your README and link to the complete receipt:
[](https://mcpqueen.com/s/io.github.trakkr-aisearch/openai-ads-mcp)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-14 22:15 | A | 92 | 2776ms |