AI agents call get_search_result to retrieve information from Archive Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries/searches archived files to return results matching a question. It retrieves data without side effects, modifying external state, or executing code. This is a classic Read operation. The semantic search (RAG) capability does not change the classification — it is still fundamentally a data retrieval function.
From the tool's definition Tool description states 'Get the list of files relevant to the question' — a retrieval operation with no modification, deletion, or execution. The verb 'get' and 'list' are explicitly read-only operations.
Documented attack patterns abuse exactly the kind of access get_search_result gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Archive Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for get_search_result:
{
"version": "1",
"default": "deny",
"tools": {
"get_search_result": {}
}
}get_search_result is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the list of files relevant to the question. It is categorised as a Read tool in the Archive Agent MCP Server, which means it retrieves data without modifying state.
Register the Archive Agent MCP server in PolicyLayer and add a rule for get_search_result: 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 Archive Agent. Nothing to install.
get_search_result 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_search_result 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_search_result. 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_search_result is provided by the Archive Agent MCP server (shredengineer/archive-agent). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Archive Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Archive Agent tools catalogued and risk-classified — across an index of 42,500+ MCP servers.