Like a LinkedIn post.
AI agents use linkedin_like_post to create or update resources in AmplifyrMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AmplifyrMCP environment.
Liking a post creates a new engagement record and modifies the post's engagement metrics. While the action is reversible (a user can unlike), it constitutes data modification. This is Write rather than Read because it changes state on the platform.
From the tool's definition Tool name 'linkedin_like_post' and description 'Like a LinkedIn post' indicate the tool creates or modifies engagement data (a 'like' action) on LinkedIn, which is a reversible write operation.
Attacks that exploit this kind of access
Like a LinkedIn post. It is categorised as a Write tool in the AmplifyrMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Amplifyr MCP server in PolicyLayer and add a rule for linkedin_like_post: 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 AmplifyrMCP. Nothing to install.
linkedin_like_post 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_like_post 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_like_post. 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_like_post is provided by the Amplifyr MCP server (supersaiyane/amplifyrmcp). 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 →