AI agents use linkedin_social_actions_like to create or update resources in Linkedin — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Linkedin environment.
Liking a post is a Write operation that creates a new 'like' record associated with the authenticated user's account. It is reversible (likes can be unliked), has moderate blast radius if misused (could like unintended content on behalf of a user), but does not delete data or move money.
From the tool's definition 'Like a LinkedIn post or comment' — performs a social action (like) that creates/modifies engagement data on LinkedIn
Attacks that exploit this kind of access
Like a LinkedIn post or comment. It is categorised as a Write tool in the Linkedin MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Linkedin MCP server in PolicyLayer and add a rule for linkedin_social_actions_like: 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 Linkedin. Nothing to install.
linkedin_social_actions_like is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the linkedin_social_actions_like 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_social_actions_like. 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_social_actions_like is provided by the Linkedin MCP server (maheidem/linkedin-optimizer-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the 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 →