Get a user by ID
AI agents call get-user to retrieve information from Harvest Time Tracking MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user information by ID without modifying, deleting, or executing any operations. It is a straightforward data lookup with no side effects. The severity is low because even if an unauthorized user is queried, the data exposure is limited to a single user record in a time-tracking system, which typically contains non-sensitive information like name and email.
From the tool's definition Tool name 'get-user' and description 'Get a user by ID' indicate a retrieval operation. The verb 'Get' and the read-only nature of fetching a single user record by identifier are consistent with the Read category.
Attacks that exploit this kind of access
Get a user by ID. It is categorised as a Read tool in the Harvest Time Tracking MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Harvest Time Tracking MCP Server MCP server in PolicyLayer and add a rule for get-user: 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 Harvest Time Tracking MCP Server. Nothing to install.
get-user 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-user 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-user. 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-user is provided by the Harvest Time Tracking MCP Server MCP server (mayank2424/mcp-server-harvest). 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 →