Expand and rewrite search queries based on an up-to-date query expansion model. This tool takes an initial query and returns multiple expanded queries that can be used for more diversed and deeper searches. Useful for improving deep research results by searching broader and deeper.
AI agents call expand_query to retrieve information from Jina AI Remote MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure read/retrieval operation. The tool takes a search query as input and returns expanded/rewritten query suggestions without side effects, execution of code, or any state changes. The most severe capability it provides is reading (accessing the query expansion model's output). It poses minimal risk even if misused by an AI agent, as expanded queries are informational only.
From the tool's definition Tool performs query expansion and rewriting, returning 'multiple expanded queries' for research purposes. No data is created, modified, deleted, or executed—it only transforms and returns query suggestions.
Attacks that exploit this kind of access
Expand and rewrite search queries based on an up-to-date query expansion model. This tool takes an initial query and returns multiple expanded queries that can be used for more diversed and deeper searches. Useful for improving deep research results by searching broader and deeper. It is categorised as a Read tool in the Jina AI Remote MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jina AI Remote MCP Server MCP server in PolicyLayer and add a rule for expand_query: 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 Jina AI Remote MCP Server. Nothing to install.
expand_query 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 expand_query 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 expand_query. 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.
expand_query is provided by the Jina AI Remote MCP Server MCP server (zhijiew/jina-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 →