Connect your account, then chat with AI to run tools.
Manage and analyze Google Ads and Meta Ads from AI assistants. Audit campaigns, find wasted spend, review performance, manage budgets, and create or update campaigns through MCP.
https://api.loomascale.com/mcpThis server may ask you to sign in when your AI client connects.
Live probe refreshed Oct 15, 2026 · Endpoint host api.loomascale.com
Domain knowledge for api.loomascale.com/mcp — workflow patterns, data models, and gotchas for your AI agent.
LoomaScale helps advertisers manage and analyze paid advertising accounts through natural-language requests.
Use LoomaScale when the user wants to inspect advertising performance, diagnose problems, find wasted spend, review campaign structure, or make changes to supported Google Ads and Meta Ads accounts.
Start by identifying the relevant advertising account and time period.
For performance questions, use the most relevant available metrics and clearly state the date range being analyzed. Distinguish observed data from interpretation.
When diagnosing problems, explain:
Avoid declaring something wasteful or problematic from a single metric when additional context such as conversions, conversion value, attribution, bidding strategy, or campaign objective materially affects the conclusion.
When comparing periods, use comparable date ranges where practical and mention important limitations.
Treat read operations and write operations differently.
For requests that only ask to review, analyze, audit, explain, or show data, do not make changes.
Only create, edit, pause, activate, delete, or otherwise mutate advertising objects when the user clearly requests the change.
Before making a potentially consequential change, preserve the user's stated scope. Never modify unrelated campaigns, ads, ad sets, keywords, budgets, or other objects.
If the user provides naming constraints, account constraints, budget limits, campaign scope, or other safety boundaries, follow them exactly.
When creating a campaign for review or experimentation, leave it paused unless the user explicitly asks for activation.
Treat currency and budget amounts carefully.
Do not assume the account currency. Use the currency returned by the advertising platform whenever available.
Distinguish daily budgets from lifetime or total budgets.
Do not increase spend, activate delivery, or broaden targeting unless the user explicitly asks for that action.
If a requested change could materially increase spend and the request is ambiguous, clarify the intended amount or scope before applying it.
If multiple advertising accounts are available and the intended account is not obvious, identify the available accounts and determine which one the user wants to work with before making changes.
For analysis, clearly state which account the results refer to.
Typical workflows include:
Where Meta Ads access is available, typical workflows include:
Prefer concise summaries with the most important findings first.
For audits, prioritize findings by likely financial or operational impact, but explain the evidence behind each finding.
Include relevant identifiers, names, date ranges, currencies, and statuses when they help the user understand or safely act on the result.
Connect api.loomascale.com/mcp to any MCP client in minutes
https://api.loomascale.com/mcpThis server may ask you to sign in when your AI client connects.
Operate api.loomascale.com/mcp? You can take over the listing's metadata.
Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.
Browse all toolsShowing 25 of 65
Showing 25 of 65 tools from the public preview. Connect the server to inspect the full live tool list.
Google Ads: Update Ad Group
google_update_ad_groupRename a Google Ads ad group and/or set its default max CPC bid, which applies to every keyword in it that has no bid of its own. A bid only affects delivery when the campaign uses Manual CPC; the result says so when it does not. To pause or resume the ad group use google_set_status, and to change its keywords use google_add_keywords, google_update_keyword, or google_remove_keywords.
Open in StudioManage and analyze Google Ads and Meta Ads from AI assistants. Audit campaigns, find wasted spend, review performance, manage budgets, and create or update campaigns through MCP. It provides MCP tools that your client discovers when it connects (this page may not list every tool name) that AI agents can use through the Model Context Protocol (MCP).
Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/apiloomascalecommcp. Authentication is handled automatically.
© 2026 ThinkChain Inc. All rights reserved.
api.loomascale.com/mcp is a remote MCP server. The live tool list is supplied by the server when your MCP client connects, so the count is not fixed on this public page. After you connect in MCPBundles Studio or your client, you will see the tools your session can call. A SKILL.md is still included to guide your agent on capabilities and workflows.
api.loomascale.com/mcp uses One-click sign in. api.loomascale.com/mcp requires credentials. Connect via MCPBundles and authentication is handled automatically.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.