AI agents call lobsters_thread to retrieve information from Devfeed without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing comment data from Lobsters without creating, modifying, deleting, or executing any operations. It has no side effects and presents minimal risk if misused by an AI agent, as the worst case would be excessive reads which Lobsters can rate-limit. Classification as Read is appropriate.
From the tool's definition Tool description states 'Get comments on a Lobsters story' - a retrieval operation with no modification or destructive capability. The verb 'Get' indicates data retrieval.
Attacks that exploit this kind of access
Get comments on a Lobsters story. It is categorised as a Read tool in the Devfeed MCP Server, which means it retrieves data without modifying state.
Register the Devfeed MCP server in PolicyLayer and add a rule for lobsters_thread: 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 Devfeed. Nothing to install.
lobsters_thread 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 lobsters_thread 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 lobsters_thread. 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.
lobsters_thread is provided by the Devfeed MCP server (upgpt-ai/devfeed-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 →