Query the LOCAL CACHE of sessions and activities. Returns only previously synced data (fast, but may be stale). To ensure fresh data: call jules_sync first, then jules_select. Best for searching across multiple sessions or filtering by type/state.
AI agents call query_cache to retrieve information from Jules MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read operation against a local cache—it retrieves and filters existing session/activity data without creating, modifying, deleting, or executing anything. The description emphasizes it returns data only and recommends calling other tools (jules_sync, jules_select) for fresh data, confirming this tool does not perform mutations.
From the tool's definition Tool description explicitly states it 'Query[s] the LOCAL CACHE of sessions and activities' and 'Returns only previously synced data'. The verb 'query' combined with read-only access to cached data indicates retrieval without side effects.
Attacks that exploit this kind of access
Query the LOCAL CACHE of sessions and activities. Returns only previously synced data (fast, but may be stale). To ensure fresh data: call jules_sync first, then jules_select. Best for searching across multiple sessions or filtering by type/state. It is categorised as a Read tool in the Jules MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jules MCP Server MCP server in PolicyLayer and add a rule for query_cache: 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 Jules MCP Server. Nothing to install.
query_cache 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 query_cache 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 query_cache. 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.
query_cache is provided by the Jules MCP Server MCP server (streetquant/jules-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 →