Score a LinkedIn post draft for engagement potential. Returns AI + heuristic
AI agents call score_content to retrieve information from SoManyLemons MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs content scoring/evaluation, which is fundamentally a read operation that analyzes existing data (a draft post) and returns analysis results. There are no side effects, no data modification, no code execution, and no irreversible actions. The return of 'AI + heuristic' scores does not constitute a write or destructive action.
From the tool's definition Tool name is 'score_content' and description states it 'Score[s] a LinkedIn post draft for engagement potential. Returns AI + heuristic' — this is a retrieval and analysis operation with no modification, creation, deletion, or external execution.
Attacks that exploit this kind of access
Score a LinkedIn post draft for engagement potential. Returns AI + heuristic. It is categorised as a Read tool in the SoManyLemons MCP MCP Server, which means it retrieves data without modifying state.
Register the SoManyLemons MCP server in PolicyLayer and add a rule for score_content: 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 SoManyLemons MCP. Nothing to install.
score_content 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 score_content 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 score_content. 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.
score_content is provided by the SoManyLemons MCP server (nomiddleinc/somanylemons-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 →