Load a pre-built Visual RAG index.
AI agents call load_rag_index to retrieve information from MedVision MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool loads a pre-existing RAG (Retrieval-Augmented Generation) index for subsequent queries or analysis. Loading is a read operation that retrieves index data into memory for use by other tools like search_similar_cases or medical_vqa. There are no side effects, no data modification, and no external operations triggered.
From the tool's definition Tool description: 'Load a pre-built Visual RAG index.' The verb 'load' indicates retrieval or initialization of an existing index without modification, creation, or deletion of data.
Attacks that exploit this kind of access
Load a pre-built Visual RAG index. It is categorised as a Read tool in the MedVision MCP MCP Server, which means it retrieves data without modifying state.
Register the MedVision MCP server in PolicyLayer and add a rule for load_rag_index: 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 MedVision MCP. Nothing to install.
load_rag_index 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 load_rag_index 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 load_rag_index. 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.
load_rag_index is provided by the MedVision MCP server (u9401066/medvision-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 →