AI agents call get_tags to retrieve information from MCP Bear without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves tag metadata from Bear Notes without creating, modifying, deleting, or executing any operations. It is a straightforward data retrieval function that poses minimal risk if misused by an AI agent, as the worst outcome would be exposure of tag information already accessible to the user.
From the tool's definition Tool name 'get_tags' and description 'Get all note tags' indicate a retrieval operation with no modification or side effects. The verb 'Get' and the stated purpose of querying tags for search purposes confirm read-only behavior.
Attacks that exploit this kind of access
Get all note tags. You can search notes by tags with get_notes_like. It is categorised as a Read tool in the MCP Bear MCP Server, which means it retrieves data without modifying state.
Register the MCP Bear MCP server in PolicyLayer and add a rule for get_tags: 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.
get_tags 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 get_tags 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 get_tags. 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.
get_tags 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 →