AI agents call get_job_summary to retrieve information from Lapras without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves job summary information without creating, modifying, deleting, or executing any operations. It has no side effects and does not affect data state. The blast radius of misuse is minimal—an agent could only fetch information already associated with a job profile, causing no irreversible harm.
From the tool's definition Tool name 'get_job_summary' and description 'Get job summary' indicate a retrieval operation with no modification capability. The verb 'Get' and the read-only nature of fetching summary data from lapras.com confirm this is a query operation.
Attacks that exploit this kind of access
Get job summary（職務要約） on LAPRAS(https://lapras.com). It is categorised as a Read tool in the Lapras MCP Server, which means it retrieves data without modifying state.
Register the Lapras MCP server in PolicyLayer and add a rule for get_job_summary: 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 Lapras. Nothing to install.
get_job_summary 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 get_job_summary 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 get_job_summary. 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.
get_job_summary is provided by the Lapras MCP server (@lapras-inc/lapras-mcp-server). 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 →