get_rsd_applications
AI agents call get_rsd_applications to retrieve information from UNHCR Population Data MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
RSD (Refugee Status Determination) applications are data entities within a humanitarian database. The 'get_' prefix, server purpose (statistics access), and peer tools all performing read operations indicate this retrieves existing application records. No indication of creation, deletion, execution, or financial impact.
From the tool's definition Tool name 'get_rsd_applications' combined with sibling tools (get_demographics_data, get_population_data, get_solutions) on a UNHCR refugee statistics server indicates a data retrieval function.
Attacks that exploit this kind of access
get_rsd_applications. It is categorised as a Read tool in the UNHCR Population Data MCP Server MCP Server, which means it retrieves data without modifying state.
Register the UNHCR Population Data MCP Server MCP server in PolicyLayer and add a rule for get_rsd_applications: 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 UNHCR Population Data MCP Server. Nothing to install.
get_rsd_applications 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_rsd_applications 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_rsd_applications. 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_rsd_applications is provided by the UNHCR Population Data MCP Server MCP server (rvibek/mcp_unhcr). 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 →