AI agents use update_version to create or update resources in Redmine — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Redmine environment.
This tool modifies existing version records (likely project versions, releases, or milestones) in a reversible manner. It falls under Write category as it creates or modifies data reversibly. Severity is medium because version updates could affect project planning, release management, and team workflows, but the change is not destructive or financial in nature and can typically be reverted.
From the tool's definition Tool name 'update_version' and description 'Update an existing version' indicate modification of version data in Redmine. The verb 'update' confirms reversible data changes without deletion or irreversible effects.
Attacks that exploit this kind of access
Update an existing version. It is categorised as a Write tool in the Redmine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Redmine MCP server in PolicyLayer and add a rule for update_version: 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 Redmine. Nothing to install.
update_version is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_version 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 update_version. 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.
update_version is provided by the Redmine MCP server (yenpu/redmine-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 →