AI agents call hn_thread_search 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 performs a search operation on thread content, which is a read-only retrieval function. It queries data but does not create, modify, delete, execute code, or move money. The blast radius is minimal as misuse would only return search results with no unintended consequences beyond information disclosure.
From the tool's definition Tool name 'hn_thread_search' and description 'Search within an HN thread for a keyword' indicate a query/search operation that retrieves data from an existing Hacker News thread without modification or side effects.
Attacks that exploit this kind of access
Search within an HN thread for a keyword. 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 hn_thread_search: 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.
hn_thread_search 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 hn_thread_search 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 hn_thread_search. 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.
hn_thread_search 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 →