AI agents call search_rnd_programs to retrieve information from Ntis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries information about national R&D programs from Korea's NTIS database. It is a read-only search function with no side effects, no data modification, no code execution, and no destructive capabilities. The blast radius of misuse is minimal — an attacker could only retrieve public information about research programs.
From the tool's definition Tool name 'search_rnd_programs' and description 'Search Korean national R&D programs' — performs a search operation with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search Korean national R&D programs (사업) — the umbrella. It is categorised as a Read tool in the Ntis MCP Server, which means it retrieves data without modifying state.
Register the Ntis MCP server in PolicyLayer and add a rule for search_rnd_programs: 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 Ntis. Nothing to install.
search_rnd_programs 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 search_rnd_programs 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 search_rnd_programs. 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.
search_rnd_programs is provided by the Ntis MCP server (vertical-mcp/ntis-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 →