AI agents call lobsters_newest 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 displays the newest stories from the Lobsters community platform. It is a read-only query operation that fetches existing data without side effects, modifications, or command execution. The blast radius of misuse is minimal—an AI agent could only retrieve unwanted information or generate unwanted digests, but cannot alter data, execute code, or create financial impacts.
From the tool's definition Tool name 'lobsters_newest' and description 'Latest stories on Lobsters' indicate a data retrieval operation with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Latest stories on Lobsters. 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_newest: 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_newest 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_newest 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_newest. 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_newest 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 →