AI agents call rerank_with_context to retrieve information from Atlas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Reranking is a retrieval operation that re-orders existing search results based on relevance scoring. It reads data to compute rankings but does not modify, delete, or execute external operations. Given the server's purpose (FHIR document search and conversation) and sibling tools like 'batch_rerank' and 'agent_query', this tool likely performs non-destructive ranking of search results.
From the tool's definition Tool name 'rerank_with_context' suggests ranking/ordering search results; no destructive, financial, or execute keywords present. Description is empty, limiting certainty.
Attacks that exploit this kind of access
rerank_with_context. It is categorised as a Read tool in the Atlas MCP Server, which means it retrieves data without modifying state.
Register the Atlas MCP server in PolicyLayer and add a rule for rerank_with_context: 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 Atlas. Nothing to install.
rerank_with_context 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 rerank_with_context 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 rerank_with_context. 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.
rerank_with_context is provided by the Atlas MCP server (rsanandres/atlas_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 →