AI agents use upload_attachment 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.
The tool uploads files to Redmine, which is a Write operation as it creates new attachment data. It is reversible (attachments can be removed), so it does not qualify as Destructive. Severity is medium because file uploads could introduce malicious content or consume storage resources, but the operation itself is not irreversible and does not directly execute code or move money.
From the tool's definition Tool description states 'Upload a file to Redmine and get a token' and 'when creating/updating issues or wiki pages to attach the file', indicating it creates/modifies data reversibly by attaching files to Redmine resources.
Attacks that exploit this kind of access
Upload a file to Redmine and get a token. Use the token when creating/updating issues or wiki pages to attach the file. 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 upload_attachment: 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.
upload_attachment 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 upload_attachment 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 upload_attachment. 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.
upload_attachment 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 →