Skip to main content
Glama

Google Business Profile MCP by InsightfulPipe

Server Details

Hosted Google Business Profile MCP server, with each action switched on or off per account.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
Insightful-Pipe/google-my-business-mcp-server
GitHub Stars
5
Server Listing
Google My Business MCP Server
ChatGPT
–
Claude
–

TDQS

A3.8/5.0

Scored across 4 tools

Disambiguation2/5

execute_action and query_data are near-verbatim duplicates in their descriptions (both labeled 'Step 3 FINAL', both with identical prerequisites and identical warning about the 'body' dictionary), so an agent cannot determine which one to call for a given task. Within query_contexts, request='available_actions' is explicitly redundant with the 'accounts' response, further blurring boundaries. Only prompts_menu is clearly distinguishable.

Naming Consistency3/5

All four names are snake_case, which is consistent, but the patterns are mixed: query_contexts/query_data share a verb_noun shape while execute_action and prompts_menu (noun-first, catalog-style) break it. Worse, the two 'query_*' names imply related behavior yet the description similarity lies between query_data and execute_action, so naming does not encode the distinctions that actually matter.

Tool Count4/5

Four tools is reasonable for a thin, workflow-oriented wrapper (discover context → resolve details → execute). The small surface is scoped appropriately, though it is on the lean side and one of the four appears to be a duplicate of another, effectively leaving three.

Completeness3/5

The generic action-passthrough design plus a context-discovery helper and prompt catalog covers the described pipeline, but there are no dedicated tools for common Google Business Profile operations (accounts/locations listing, reviews, posts), forcing every read and write through an opaque 'body' dictionary. The split between execute_action and query_data is never resolved, leaving a functional dead end for the agent.

Available Tools

4 tools
execute_actionGMB Execute ActionA
Destructive
Inspect

Execute Google My Business actions (Step 3 FINAL).

Prerequisites: Run query_contexts with request='accounts' (includes available_actions) + request='actions_details' to understand the required payload.

IMPORTANT: The 'body' parameter is a dictionary that must contain ALL fields including:

  • action: Table/action name from available_actions

  • workspace_id: Integer workspace ID

  • brand_id: Integer brand ID

  • location_id: Location identifier

  • Any other fields from the helper response (filters, date ranges, etc.)

Do NOT pass these as separate parameters - they must ALL be inside the body dictionary.

Inputs: body (required). Returns: object

prompts_menuGMB PromptsA
Read-only
Inspect

Browse the Google My Business prompt catalog.

  1. request='menu' – List public/system prompts (optionally pass workspace_id + prompt_type).

  2. request='prompt_details' – Fetch prompt body by prompt_id. Set is_custom=True + workspace_id for workspace prompts.

Inputs: request (required), is_custom, prompt_id, prompt_type, +1 more. Returns: object

query_contextsGMB Setup HelperA
Read-only
Inspect

Helper for planning InsightfulPipe Google My Business data queries.

Step 1: request='accounts' – Retrieve workspace_id, brand_id, location_id, other source metadata, AND available_actions (all tables you can query).

Step 2: request='actions_details' with actions=['xxxxxx', 'xxxxxx', 'xxxxxx'] – REQUIRED before querying. Replace with actions from available_actions to get the exact request body, required identifiers, fields, time ranges, and notes for each action.

Optional: request='available_actions' – Standalone call to list all available tables/actions (already included in accounts response).

Optional: request='brands' with brand_id + workspace_id to pull brand guidelines.

Inputs: request (required), actions, brand_id, platform, +1 more. Returns: object

query_dataGMB Data QueryA
Read-only
Inspect

Execute Google My Business data queries (Step 3 FINAL).

Prerequisites: Run query_contexts with request='accounts' (includes available_actions) + request='actions_details' to understand the required payload.

IMPORTANT: The 'body' parameter is a dictionary that must contain ALL fields including:

  • action: Table/action name from available_actions

  • workspace_id: Integer workspace ID

  • brand_id: Integer brand ID

  • location_id: Location identifier

  • Any other fields from the helper response (filters, date ranges, etc.)

Do NOT pass these as separate parameters - they must ALL be inside the body dictionary.

Inputs: body (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      A hosted MCP server that enables managing Google Ads, Microsoft Advertising, TikTok Ads, LinkedIn Ads, and other Google services from ChatGPT, Claude, or any MCP client using natural language, with no code or API keys required.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that provides 40 tools for managing Google Business Profiles, including accounts, locations, verifications, reviews, and performance analytics, enabling AI agents to interact with GBP via REST APIs.
      4
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      A hosted remote MCP server that connects marketing platforms such as Google Ads, GA4, Search Console, Meta Ads, Microsoft Ads, LinkedIn Ads, TikTok Ads, and Google Business Profile, enabling plain-English performance analysis, KPI and budget tracking, report creation, and previewed account changes.
      8
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.