AI agents call rank_aggregate to retrieve information from Liana-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs aggregation and retrieval of existing cell-cell communication analysis results. It computes summary statistics across multiple methods but does not create, modify, delete, or execute external operations. This is a quintessential Read operation on analytical data derived from scRNA-Seq analysis.
From the tool's definition Tool description states 'Get an aggregate of ligand-receptor scores from multiple Cell-cell communication methods.' The verb 'Get' and the read-only nature of aggregating pre-computed scores indicates data retrieval without modification or side effects.
Attacks that exploit this kind of access
Get an aggregate of ligand-receptor scores from multiple Cell-cell communication methods. It is categorised as a Read tool in the Liana-MCP MCP Server, which means it retrieves data without modifying state.
Register the Liana- MCP server in PolicyLayer and add a rule for rank_aggregate: 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 Liana-MCP. Nothing to install.
rank_aggregate 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 rank_aggregate 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 rank_aggregate. 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.
rank_aggregate is provided by the Liana- MCP server (scmcphub/liana-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 →