AI agents use rename_tag to create or update resources in MCP Bear — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Bear environment.
This tool modifies existing data (tag names) reversibly across notes. Users could undo the rename by renaming again, making it a Write operation rather than Destructive. The blast radius is medium because renaming a tag affects all notes with that tag, but the operation is reversible and does not irreversibly delete or destroy data.
From the tool's definition The tool description explicitly states 'Rename a tag across all notes', which is a modification operation that updates data (tag names) across multiple notes.
Attacks that exploit this kind of access
Rename a tag across all notes. It is categorised as a Write tool in the MCP Bear MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Bear MCP server in PolicyLayer and add a rule for rename_tag: 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 MCP Bear. Nothing to install.
rename_tag 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 rename_tag 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 rename_tag. 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.
rename_tag is provided by the MCP Bear MCP server (maxim-ist/mcp-bear). 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 →