toolfare

Ask your AI which search terms are burning your budget.

CPA and ROAS by campaign, keyword and search-term reports, recommendations with their estimated impact, change history and Performance Max structure — answered inside ChatGPT, Claude, Codex or Cursor. Connect your Google Ads account to toolfare once; your AI reads it with your own login, and every read costs 0 credits.

Start Asking For FreeConnect in 1 Click

Set it up in

Claude CodeCodexCursorVS CodeChatGPTClaude (web & desktop)Your own agent
toolfare

Sign in, connect the account once, paste the setup prompt to your agent, ask something. That’s the whole setup.

Your accounts, one connection

ads, analytics, commerce and revenue

Google Ads

Campaigns, keywords and search terms

Meta Ads

CPA and delivery on Facebook and Instagram

TikTok Ads

Spend, results, Smart+ and GMV Max reporting

200+

APIs

40+

apps

30+

skills

Ask once and your AI reads the accounts you connected — no paid data call involved.

Your own account0 credits per readNew ads need your approval
About five minutes

Set it up once, in the app you already use.

Connect your Google Ads account in toolfare once. After that, every AI app you approve reads it through the same connection, with nothing to install for Google Ads itself.

Claude Code

Use the MCP connection in your AI app, or run the toolfare CLI in its terminal. Both use browser approval, discover capabilities and quote paid calls before they run.

  1. 1

    Create your toolfare workspace

    The connection is public and identical for everyone — your toolfare sign-in is what points it at your data. Connect one account in that workspace too: that is what your AI reads. The first time your AI uses the connection, toolfare asks you to approve the access and names the workspace it will read through. No workspace yet? toolfare has you create one right there, then brings you back to approve.

    Create your workspace

    Already have one? Nothing to do here — sign in when the connection asks for it.

  2. 2

    Copy the toolfare MCP connection

    https://api.toolfare.ai/mcp
  3. 3

    Add it to Claude Code

    claude mcp add --transport http toolfare https://api.toolfare.ai/mcp
    1. Run the command in any project. It writes the configuration and prints an `Added …` line.
    2. Authorize separately — adding a server does not open a browser.
    3. Run `claude mcp list` to confirm the server reads `✔ Connected`.
  4. 4

    Approve the access, then ask it something

    1. Inside Claude Code, run `/mcp` and follow the browser flow — or, from your shell, `claude mcp login toolfare`.
    2. The toolfare consent page names the host, the workspace the grant will read through, and what the connection will be able to do.
    3. Approving creates the grant listed above on this page. Cancelling creates nothing.
    4. On a machine with no browser (SSH, headless Linux), `claude mcp login toolfare --no-browser` prints the URL and takes the pasted callback.

    Paste this first

    Using toolfare, search for what capabilities I can reach.

    A list of capabilities with names, what each reads and what each costs. An empty list means the search matched nothing — try broader words. An error naming authorization means the host never completed the browser step.

Checked 2026-08-25 against Claude Code documentation. Menu names change between releases — look for connectors, apps, tools or integrations.

Open the console to connect your accounts
30 things you can ask it

Ask in plain English. These are the tools behind the answer.

Each one is a tool your AI is offered by name once you connect. You never have to type the name — it is here so you can tell what actually ran.

  • CPA and ROAS by campaign, ad group or day

    ads_query_single_dimension

    Spend, clicks, conversions, CPA and ROAS, grouped by one dimension over a date range — read from toolfare’s synced copy of the account, so a whole quarter answers in one call.

    • “What was our Google Ads CPA by campaign last month?”
    • “Which campaigns had the best ROAS in the last 30 days?”

  • Keyword and search-term reports, ready-made

    ads_get_google_ads_report

    Account, campaign, ad, keyword, search-term and bidding-strategy reports with fixed columns, read live — the last 30 days unless you name a range.

    • “Which search terms spent the most without converting?”
    • “Show me the keyword report for the last 30 days.”

  • Any Google Ads field, through GAQL

    ads_gaql_search

    A live Google Ads Query Language search for the fields, segments and combinations the ready-made reports do not expose — responsive search ad headlines, device by hour, and the like.

    • “Pull the headlines on our responsive search ads.”
    • “Break down clicks by device and hour of day for this campaign.”

  • Google’s recommendations, with their impact

    ads_get_recommendations

    The account’s automated recommendations — add keywords, raise a budget, change bidding — each with the baseline and the estimated change in impressions, clicks and cost.

    • “What does Google recommend for this account, and what would it change?”
    • “Which recommendations have the biggest estimated impact?”

  • Who changed what, and from where

    ads_get_change_history

    Google’s own change events: the user, the fields that changed, and whether it came from the UI, the API or an automated rule.

    • “Who changed bids on this campaign last week?”
    • “Did an automated rule change anything before the drop?”

  • Inside a Performance Max campaign

    ads_get_pmax_campaign

    One Performance Max campaign with its asset groups, final URLs, asset attachments and the approval state of its signals.

    • “What asset groups does our Performance Max campaign have?”
    • “Are the signals on this PMax campaign approved?”

And 24 more, same connection

Named rather than worked through — your AI discovers all of them through the connection itself, so you never have to pick one.

  • Audit every tracked automation setting against the live accountads_audit_ad_automation_inventory
  • Check whether AI-automation settings drifted from what was approvedads_audit_creative_automation
  • Draft a paused ad from a creativeads_create_ad
  • One portfolio bidding strategyads_get_bidding_strategy
  • One campaign’s live settings and statusads_get_campaign
  • Installable conversion tag snippetsads_get_conversion_tracking_snippets
  • Which date ranges have finished syncingads_get_data_readiness
  • Whether conversion tracking is ready for a conversion campaignads_get_deploy_readiness
  • Whether offline conversions are set up to be receivedads_get_offline_conversion_readiness
  • Which fields a GAQL resource can select and filterads_get_resource_metadata
  • The accounts under a manager (MCC) accountads_get_tree_structure
  • Account-level negative keywordsads_list_account_negative_keywords
  • The ad accounts this workspace can readads_list_ad_accounts
  • An ad group’s negative keywordsads_list_ad_group_negative_keywords
  • The ads in an account, campaign or ad groupads_list_ads
  • Portfolio Target CPA and Target ROAS strategiesads_list_bidding_strategies
  • A campaign’s negative keywordsads_list_campaign_negative_keywords
  • Every campaign, with live status and budgetads_list_campaigns
  • The conversion actions the account tracksads_list_conversion_actions
  • Country targeting codesads_list_countries
  • The customer accounts your login can reachads_list_customers
  • Language targeting codesads_list_languages
  • Read an entity’s current automation settingsads_preview_automation_baseline
  • Performance broken down by several dimensions at onceads_query_multi_dimension
Pricing

Buy toolfare credits for your research and agent workflow.

Pay as you go. Buy credits when you need them, with no subscription.

Pay as you go

10,000 credits from $30

Buy credits when you need them. No subscription. Every paid call is quoted before it runs.

Buy credits