adcrunch

Query live ad campaign data across Meta, TikTok, and Google Ads in natural language — no SQL, no dashboards.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • List Advertisers: List ad accounts (advertisers) connected to the active organization. Optionally filter by provider (meta, gads, tiktok, snapchat, dv360).
  • List Campaigns: List campaigns under an advertiser connected to the active organization. Optionally filter by campaign IDs.
  • List Ad Groups: List ad groups (also called ad sets on Meta) under an advertiser connected to the active organization. Optionally filter by campaign or ad group IDs.

What data it sees

Do you need an account

No: the server works without sign-in

Query live ad campaign data across Meta, TikTok, and Google Ads in natural language — no SQL, no dashboards.

How to connect

How to connect adcrunch to Claude

The server address to paste into Claude settings:

https://adcrunch.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect adcrunch to ChatGPT

The server address to paste into ChatGPT settings:

https://adcrunch.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect adcrunch to Cursor

The server address to paste into Cursor settings:

https://adcrunch.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (11)

Raw names from tools/list. Only developers need these.

list_advertisersList ad accounts (advertisers) connected to the active organization. Optionally filter by provider (meta, gads, tiktok, snapchat, dv360).
list_campaignsList campaigns under an advertiser connected to the active organization. Optionally filter by campaign IDs.
list_ad_groupsList ad groups (also called ad sets on Meta) under an advertiser connected to the active organization. Optionally filter by campaign or ad group IDs.
list_adsList ads under an advertiser connected to the active organization. Optionally filter by campaign IDs or ad IDs.
query_insightsQuery advertising insights/metrics for an advertiser. Supports breakdown by campaign / ad-group / ad, time intervals (day/week/month), date ranges (since/until or a relative window like last_7_days), and metric selection (spend, impressions, clicks, ctr, cpm, roas, etc.). Defaults to spend + impressions over the last 15 days when no date range is provided.
search_adsSearch a provider ad library **live** — the query hits the Meta Ad Library or the TikTok Commercial Content Library at call time and returns the current results (no stored corpus, no AI enrichment). A single call targets exactly one `provider`. The two providers have different required filters: - `meta`: `country` is **required** (the archive endpoint mandates a reached-country). - `tiktok`: `dateFrom` and `dateTo` (`YYYYMMDD`) are **required** (the research endpoint mandates a published-date window). Paginate by passing the `cursor` returned by a previous call back into the next one. Results are bounded by what the provider returns for the page; there is no relevance ranking or semantic match.
skill_listList the active organization's ad-ops playbooks (Skills) as slug + name + description. Bodies are not returned — fetch a Skill's instructions with skill_get once you've picked one.
skill_getFetch a single ad-ops playbook (Skill) by its slug, returning the full instruction body and the current revision. Echo the revision back as base_revision when updating the Skill.
skill_createCreate an ad-ops playbook (Skill) in the active organization. The slug (its stable handle) is derived from the name unless an explicit slug is provided. Fails if a Skill with the same slug already exists in the organization.
skill_updateUpdate an ad-ops playbook (Skill). Pass base_revision (from skill_get) — the update is rejected if the Skill changed since you read it. Only the fields you pass are changed. Optionally rename the slug handle.
skill_deleteDelete an ad-ops playbook (Skill). Pass base_revision (from skill_get) — the delete is rejected if the Skill changed since you read it. The slug becomes free to re-use afterwards.