AI agents call check_version_compatibility to retrieve information from Citrix without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries information about Citrix product versions, compatibility status, and upgrade recommendations. It performs no modifications, executions, deletions, or financial transactions. The operation is entirely read-based with no side effects, making it the lowest risk category.
From the tool's definition Tool description states it 'checks' whether a version is end-of-life and compatible—purely informational/query operations with no modifications or side effects. Keywords: 'Check', 'verify' indicate read-only status.
Attacks that exploit this kind of access
Check whether a specific Citrix product version is end-of-life, LAS-compatible, and what version to upgrade to. It is categorised as a Read tool in the Citrix MCP Server, which means it retrieves data without modifying state.
Register the Citrix MCP server in PolicyLayer and add a rule for check_version_compatibility: 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 Citrix. Nothing to install.
check_version_compatibility 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 check_version_compatibility 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 check_version_compatibility. 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.
check_version_compatibility is provided by the Citrix MCP server (skipmiller/citrix-mcp-server). 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 →