Fallback: GET any LinkedIn /rest endpoint not covered by named tools. Read-only. Prefer linkedin.account.overview, linkedin.campaigns.list, linkedin.analytics, linkedin.creatives.list when those fit.
AI agents call linkedin.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.
This tool performs HTTP GET requests to LinkedIn REST endpoints without modifying, creating, or deleting data. The explicit 'Read-only' designation and GET method confirm it retrieves data without side effects. The low severity reflects the minimal blast radius of read-only access to LinkedIn ad account data, even with broad endpoint coverage.
From the tool's definition Tool name contains 'read' and description explicitly states 'Read-only' and 'GET any LinkedIn /rest endpoint'. The description emphasizes it is a fallback for read operations and recommends preferring specific named tools for queries.
Attacks that exploit this kind of access
Fallback: GET any LinkedIn /rest endpoint not covered by named tools. Read-only. Prefer linkedin.account.overview, linkedin.campaigns.list, linkedin.analytics, linkedin.creatives.list when those fit. It is categorised as a Read tool in the Ads MCP Server, which means it retrieves data without modifying state.
Register the Ads MCP server in PolicyLayer and add a rule for linkedin.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.
linkedin.passthrough.read is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the linkedin.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.
Set action: deny in the PolicyLayer policy for linkedin.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.
linkedin.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.
linkedin.passthrough.read is one line of Ads's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →