Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Google Ads MCP

PYPI · SCALABLY-GOOGLE-ADS-MCP · 2 COMPONENTS · SCANNED SEP 20

Google Ads MCP: GAQL queries, resources, recommendations, keyword ideas, change history. 11 tools.

+5 this week 70 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 1 of 51 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability57
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2438 tokens (~221/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
  • Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the Google Ads MCP server?

Google Ads MCP runs locally as a PyPI package, launched with uvx scalably-google-ads-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · scalably-google-ads-mcp

# add to Claude Code
claude mcp add io-scalably-google-ads-mcp -- uvx scalably-google-ads-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "io-scalably-google-ads-mcp": {
      "command": "uvx",
      "args": [
        "scalably-google-ads-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "io-scalably-google-ads-mcp": {
      "command": "uvx",
      "args": [
        "scalably-google-ads-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add io-scalably-google-ads-mcp -- uvx scalably-google-ads-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-scalably-google-ads-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "scalably-google-ads-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add io-scalably-google-ads-mcp --command uvx --arg scalably-google-ads-mcp
# ~/.hermes/config.yaml
mcp_servers:
  io-scalably-google-ads-mcp:
    command: "uvx"
    args: ["scalably-google-ads-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "io-scalably-google-ads-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "scalably-google-ads-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add io-scalably-google-ads-mcp -t stdio -c uvx -a scalably-google-ads-mcp
// mcp.json
{
  "mcpServers": {
    "io-scalably-google-ads-mcp": {
      "command": "uvx",
      "args": [
        "scalably-google-ads-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Sept 26 +16
    • Malware scan: unverified → pass security
  • 17 Sept 26 −14
    • Malware scan: pass → unverified security
  • 16 Sept 26 +3
    • Stability: unverified → 0.23 functional
  • 15 Sept 26 +15
    • Malware scan: unverified → pass security
  • 14 Sept 26 −15
    • Malware scan: pass → unverified security
  • 12 Sept 26 +15
    • Malware scan: unverified → pass security
  • 11 Sept 26 −15
    • Malware scan: pass → unverified security
  • 10 Sept 26 +15
    • Malware scan: unverified → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/scalably-google-ads-mcp@1.0.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 51 packages
Packages resolved 51
Stale 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 11 exposed · ~2,438 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
google_ads_change_events ~181

Audit trail: who changed what in the last 30 days. Max window is 30 days back. Returns: change_date_time, user_email, change_resource_type (CAMPAIGN|AD_GROUP|AD_GROUP_CRITERION|CAMPAIGN_BUDGET| AD|AD_GROUP_BID_MODIFIER|…), old_resource, new_resource, changed_fields, client_type (GOOGLE_ADS_WEB_CLIENT|GOOGLE_ADS_API|…). Args: customer_id: 10-digit customer_id. days_back: 1–30. resource_types: optional filter to specific change_resource_type enum values. limit: max rows (default 10000, capped 100000).

NameTypeReqDescription
customer_idstringyes
days_backinteger
limitinteger
resource_types
NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_change_status ~121

Lightweight change tracker: last-modified-at timestamps for resources. Unlike change_event, this is a per-resource "last modified" view rather than a change-diff log. Covers up to 14 days. Args: customer_id: 10-digit customer_id. days_back: 1–14. resource_types: optional filter by change_status.resource_type enum. limit: max rows.

NameTypeReqDescription
customer_idstringyes
days_backinteger
limitinteger
resource_types
NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_describe_resource ~180

Schema (fields, metrics, segments) for a GAQL resource. Queries GoogleAdsFieldService for every selectable field on a resource plus its data type, selectability, filterability, sort-ability, and `selectable_with` (which other fields can coexist in a single SELECT). Args: resource_name: the GAQL resource, e.g. "campaign", "ad_group", "shopping_performance_view", "change_event", "recommendation". Returns: {resource, fields: [{name, category: ATTRIBUTE|METRIC|SEGMENT, data_type, selectable, filterable, sortable, enum_values, type_url, selectable_with}]}. Essential before composing GAQL on an unfamiliar resource; prevents FIELD_NOT_COMPATIBLE and FIELD_NOT_FOUND errors.

NameTypeReqDescription
resource_namestringyes
NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_keyword_forecast_metrics ~201

Forecast KPIs (impressions, clicks, cost, conversions) for a proposed keyword plan. Args: customer_id: 10-digit customer_id. campaign_spec: a KeywordPlanCampaign forecast spec. Minimum shape: { "bidding_strategy": "MANUAL_CPC", "daily_budget_micros": 10000000, "keyword_match_type": "BROAD" | "PHRASE" | "EXACT", "language_id": "1000", "geo_target_ids": ["2840"], "keywords": ["running shoes", "trail running shoes"] } Returns: {campaign_forecast: {impressions, clicks, cost_micros, conversions, average_cpc_micros}, weekly_time_series: [...]}. Rate limit: 1 QPS. Requires Basic Access.

NameTypeReqDescription
campaign_specobjectyes
customer_idstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_keyword_historical_metrics ~222

Historical monthly search-volume + competition metrics for specific keywords. Args: customer_id: 10-digit customer_id. keywords: list of keyword strings (max 10,000 per call). language_id / geo_target_ids / keyword_network: same shape as keyword_ideas. year_month_start / year_month_end: optional date range as {year: 2025, month: 1..12}. Defaults to last 12 months. Returns: {results: [{text, approximate_monthly_searches, monthly_search_volumes: [{year, month, monthly_searches}], competition, high/low_top_of_page_bid_micros}]}. Rate limit: 1 QPS. May require Basic Access.

NameTypeReqDescription
customer_idstringyes
geo_target_ids
include_adultboolean
keyword_networkstring
keywordsarrayyes
language_idstring
year_month_end
year_month_start
NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_keyword_ideas ~361

Generate keyword ideas with search volume + competition + CPC estimates. Args: customer_id: customer_id to attribute the request (any Ads account under MCC works). keywords: seed keywords, list of strings. Optional if page_url is given. page_url: seed URL (crawled for keyword extraction). Optional if keywords given. language_id: Google language criterion ID. Default '1000' (English). Common: '1001' Spanish, '1002' French, '1003' German, '1007' Italian. geo_target_ids: list of geo criterion IDs. Default ['2840'] (US). Common: '2826' UK, '2124' Canada, '2036' Australia, '2276' Germany. keyword_network: GOOGLE_SEARCH (default) | GOOGLE_SEARCH_AND_PARTNERS. include_adult: include adult-category keywords (default False). page_size: max ideas to return (default 100, capped at 10000). Returns: {ideas: [{text, avg_monthly_searches, competition, low_top_of_page_bid_micros, high_top_of_page_bid_micros, concept_group}]}. Rate limit: 1 QPS for this service. Back off on RESOURCE_EXHAUSTED. Requires Basic Access (Explorer may 403); if you get USER_PERMISSION_DENIED, the dev_token tier is too low.

NameTypeReqDescription
customer_idstringyes
geo_target_ids
include_adultboolean
keyword_networkstring
keywords
language_idstring
page_sizeinteger
page_url
NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_list_accessible_customers ~96

List every customer_id the OAuth user has direct access to. This is a small, cheap list, typically just the MCC itself and any standalone accounts. For the full tree of accounts under the MCC (agency use case), call google_ads_list_customer_clients instead. Returns: {"resource_names": [...], "customer_ids": [...]}. Each customer_id is 10 digits, no hyphens.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_list_customer_clients ~215

Walk the MCC (Manager Account) hierarchy and return every child account. For agency use: this is the canonical "which clients can I query?" call. Uses GAQL on the `customer_client` resource. Fast: one streaming call. Args: mcc_customer_id: MCC customer_id. Defaults to GOOGLE_ADS_LOGIN_CUSTOMER_ID (the configured MCC). Accepts 10-digit or hyphenated. include_managers: include sub-MCCs in the result (default True). include_hidden: include customer_clients marked hidden=True (default False). max_level: max hierarchy depth (default 3, hard cap 10). Returns per account: customer_id, descriptive_name, currency_code, time_zone, manager (bool), level, status (ENABLED|CANCELED|…), hidden, resource_name.

NameTypeReqDescription
include_hiddenboolean
include_managersboolean
max_levelinteger
mcc_customer_id
NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_list_resources ~69

Return the full catalog of GAQL resources (FROM-able tables). Useful when the agent needs to pick the right resource for a question. Each entry: name, category, selectable (whether it can be the FROM target). Response is cacheable for the session; the catalog is stable across queries.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_query ~532

Run a GAQL (Google Ads Query Language) query against a specific customer account. GAQL is SQL-like: `SELECT ... FROM <single_resource> WHERE ... ORDER BY ... LIMIT ...`. No JOINs; attribute fields from related resources by selecting them directly. Common resources: campaign, ad_group, keyword_view, search_term_view, shopping_performance_view, customer, customer_client, conversion_action, change_event, change_status, recommendation, asset, asset_group. Use google_ads_describe_resource first if unsure of field names on a new resource; saves a FIELD_NOT_FOUND roundtrip. Args: customer_id: 10-digit customer_id (no hyphens) for the account to query. gaql: the full GAQL query string (must start with SELECT; no semicolons). max_rows: if set, stop streaming after this many rows. Defaults to unbounded (the 64 MB response cap still applies). convert_micros: if True (default), also emit <metric>_units alongside any <metric>_micros field (divided by 1,000,000). E.g. cost_micros = 12345678 → cost_units = 12.345678. Example queries: SELECT campaign.id, campaign.name, metrics.cost_micros FROM campaign WHERE segments.date DURING LAST_7_DAYS ORDER BY metrics.cost_micros DESC LIMIT 50 SELECT ad_group.name, ad_group_criterion.keyword.text, metrics.impressions, metrics.clicks FROM keyword_view WHERE segments.date DURING LAST_30_DAYS SELECT segments.product_item_id, metrics.conversions_value FROM shopping_performance_view WHERE segments.date DURING LAST_30_DAYS Gotchas (surface to user where relevant): - metrics.cost_micros: 1 unit = $0.000001. Divide by 1M for currency. - LAST_30_DAYS = 30 days ending YESTERDAY (today excluded). - Last 72h data is partial; conversions retroactively re-attribute. - Zero-metric rows are excluded when segmenting by date. - Response cap is 64 MB per call; split by date range for huge reports. - GAQL `IN (...)` clause is capped at 20,000 items.

NameTypeReqDescription
convert_microsboolean
customer_idstringyes
gaqlstringyes
max_rows
NameTypeReqDescription
resultstringyes

No examples provided.

google_ads_recommendations ~260

Read Google's optimization recommendations for a customer account. Returns suggestions only; does NOT apply any. Types include: KEYWORD, CAMPAIGN_BUDGET, KEYWORD_MATCH_TYPE, TARGET_CPA_OPT_IN, MAXIMIZE_CLICKS_OPT_IN, OPTIMIZE_AD_ROTATION, RESPONSIVE_SEARCH_AD, ENHANCED_CPC_OPT_IN, SEARCH_PARTNERS_OPT_IN, SITELINK_EXTENSION, CALL_EXTENSION, CALLOUT_EXTENSION, STRUCTURED_SNIPPET_EXTENSION, DISPLAY_EXPANSION_OPT_IN, KEYWORD_MATCH_TYPE, FORECASTING_*, SHOPPING_*, MOVE_UNUSED_BUDGET. (Google adds new types over time.) Args: customer_id: 10-digit account ID. types: optional list to filter by recommendation_type. Case-sensitive. dismissed: include dismissed recommendations (default False). limit: max rows (default 200). Each row contains: type, impact (absolute_metrics, base_metrics, potential_metrics), campaign / ad_group ref (if applicable), dismissed flag, recommendation-specific payload (e.g. suggested_keywords, budget_increase).

NameTypeReqDescription
customer_idstringyes
dismissedboolean
limitinteger
types
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the Google Ads MCP server?

Google Ads MCP is listed in the public MCP registry as io.scalably/google-ads-mcp. Google Ads MCP: GAQL queries, resources, recommendations, keyword ideas, change history. 11 tools. This page covers its PyPI package (scalably-google-ads-mcp).

Is the Google Ads MCP server safe to use?

Google Ads MCP scores 70 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Google Ads MCP server expose?

Google Ads MCP exposes 11 tools: google_ads_list_accessible_customers, google_ads_list_customer_clients, google_ads_query, google_ads_describe_resource, google_ads_list_resources, and 6 more. Their descriptions and schemas cost roughly 2,438 tokens of context every time the server is loaded.

Is the Google Ads MCP server still maintained?

Google Ads MCP is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Google Ads MCP server under?

Google Ads MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.