ga4.passthrough.read

Fallback: call any GA4 Data API method (POST) or Admin API GET endpoint not yet covered by named tools. Read-only. Prefer ga4.report.run, ga4.report.realtime, ga4.report.batch, ga4.report.pivot, ga4.accounts.list, ga4.properties.* when those fit.

Server Ads manlikemuneeb/ads-mcp
Category Read
Risk class Low
Parameters 00 required

What ga4.passthrough.read does on Ads

AI agents call ga4.passthrough.read to retrieve information from Ads without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why ga4.passthrough.read needs a policy

The tool is explicitly labeled read-only and is intended for GET or POST-based Data API reads. However, it's a passthrough/fallback that can call arbitrary GA4 endpoints not yet covered by named tools, which introduces some risk that a misconfigured or malicious call could access broad data. The blast radius is medium since it's limited to GA4 data reads but can access any endpoint.

From the tool's definition Fallback: call any GA4 Data API method (POST) or Admin API GET endpoint not yet covered by named tools. Read-only.

Risk signalsAdmin/system-level operation

Questions about ga4.passthrough.read

What does the ga4.passthrough.read tool do? +

Fallback: call any GA4 Data API method (POST) or Admin API GET endpoint not yet covered by named tools. Read-only. Prefer ga4.report.run, ga4.report.realtime, ga4.report.batch, ga4.report.pivot, ga4.accounts.list, ga4.properties.* when those fit. It is categorised as a Read tool in the Ads MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ga4.passthrough.read? +

Register the Ads MCP server in PolicyLayer and add a rule for ga4.passthrough.read: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ads. Nothing to install.

What risk level is ga4.passthrough.read? +

ga4.passthrough.read is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ga4.passthrough.read? +

Yes. Add a rate_limit block to the ga4.passthrough.read rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block ga4.passthrough.read completely? +

Set action: deny in the PolicyLayer policy for ga4.passthrough.read. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides ga4.passthrough.read? +

ga4.passthrough.read is provided by the Ads MCP server (manlikemuneeb/ads-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.