List recent versions of a model, newest first.
AI agents call list_versions to retrieve information from Bim Change Engine without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns version history metadata without creating, modifying, deleting, or executing any operations. It is a straightforward read operation with minimal risk if misused by an agent—the worst outcome would be exposure of existing version information.
From the tool's definition Tool name 'list_versions' and description 'List recent versions of a model, newest first' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List recent versions of a model, newest first. It is categorised as a Read tool in the Bim Change Engine MCP Server, which means it retrieves data without modifying state.
Register the Bim Change Engine MCP server in PolicyLayer and add a rule for list_versions: 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 Bim Change Engine. Nothing to install.
list_versions 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 list_versions 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 list_versions. 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.
list_versions is provided by the Bim Change Engine MCP server (rishibajaj-prodman/bim-change-engine). 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 →