Plan an efficient read using properties and includeReferencedEntities where possible.
AI agents call plan_cross_entity_read to retrieve information from Weclapp Api Knowledge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool plans and executes read operations across entities, using GET-style retrieval with no write or destructive side effects. The description explicitly mentions 'read' and 'includeReferencedEntities', indicating data retrieval only. Severity is low as it only queries data.
From the tool's definition Plan an efficient read using properties and includeReferencedEntities where possible
Attacks that exploit this kind of access
Plan an efficient read using properties and includeReferencedEntities where possible. It is categorised as a Read tool in the Weclapp Api Knowledge MCP Server, which means it retrieves data without modifying state.
Register the Weclapp Api Knowledge MCP server in PolicyLayer and add a rule for plan_cross_entity_read: 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 Weclapp Api Knowledge. Nothing to install.
plan_cross_entity_read 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 plan_cross_entity_read 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 plan_cross_entity_read. 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.
plan_cross_entity_read is provided by the Weclapp Api Knowledge MCP server (serenmind/weclapp-api-knowledgebase-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 →