Search project documentation using RAG. Retrieves relevant documentation chunks based on semantic similarity. Use this to find information about the EasyPomodoro project architecture, features, and implementation details.
AI agents call rag_query to retrieve information from Weather Forecast 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 semantic search over project documentation, returning matching information without side effects. It is a pure retrieval operation that queries existing data. The sibling tools (get_project_structure, get_spec_content, list_specs, rebuild_index) and the server description context do not alter this classification—rag_query itself is a Read operation with minimal security risk.
From the tool's definition Tool description states it 'Retrieves relevant documentation chunks based on semantic similarity' and 'find information about' project documentation.
Attacks that exploit this kind of access
Search project documentation using RAG. Retrieves relevant documentation chunks based on semantic similarity. Use this to find information about the EasyPomodoro project architecture, features, and implementation details. It is categorised as a Read tool in the Weather Forecast MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Weather Forecast MCP Server MCP server in PolicyLayer and add a rule for rag_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 Weather Forecast MCP Server. Nothing to install.
rag_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 rag_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 rag_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.
rag_query is provided by the Weather Forecast MCP Server MCP server (lebedaliv2601/mcpsystem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
rag_query is one line of Weather Forecast MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →