AI agents call update_check to retrieve information from Kb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads/queries version information from PyPI (a public package registry) to compare against the installed version. It has no side effects, does not modify any data, and cannot cause harm if misused — it simply fetches metadata.
From the tool's definition Check if a newer version of kb-mcp is available on PyPI
Attacks that exploit this kind of access
Check if a newer version of kb-mcp is available on PyPI. It is categorised as a Read tool in the Kb MCP Server, which means it retrieves data without modifying state.
Register the Kb MCP server in PolicyLayer and add a rule for update_check: 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 Kb. Nothing to install.
update_check 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 update_check 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 update_check. 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.
update_check is provided by the Kb MCP server (okash1n/kb). 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 →