AI agents call search_3gpp_docs to retrieve information from 3gpp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only search tool. It queries and retrieves information from 3GPP technical specifications. There are no side effects, data modifications, code execution, financial transactions, or destructive operations. Even in legacy mode, it remains a data retrieval operation.
From the tool's definition Tool performs "Search 3GPP specification documents by keywords" - a query operation that retrieves information from pre-processed 3GPP specification data without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
Search 3GPP specification documents by keywords (legacy mode). It is categorised as a Read tool in the 3gpp MCP Server, which means it retrieves data without modifying state.
Register the 3gpp MCP server in PolicyLayer and add a rule for search_3gpp_docs: 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 3gpp. Nothing to install.
search_3gpp_docs 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_3gpp_docs 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_3gpp_docs. 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_3gpp_docs is provided by the 3gpp MCP server (lee-sihyeon/mcp-server-3gpp). 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 →