Create a new list or update an existing one. Requires authentication.
AI agents use upsert_list to create or update resources in Bandmate MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bandmate MCP Server environment.
This tool creates or updates playlists/lists, which are data structures that can be modified or deleted later. There is no irreversible destruction, financial obligation, or code execution involved. The 'Requires authentication' note indicates access control is in place.
From the tool's definition Tool name 'upsert_list' and description 'Create a new list or update an existing one' directly indicate reversible creation or modification of list data. The verb 'upsert' (update or insert) is a classic Write operation.
Attacks that exploit this kind of access
Create a new list or update an existing one. Requires authentication. It is categorised as a Write tool in the Bandmate MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bandmate MCP Server MCP server in PolicyLayer and add a rule for upsert_list: 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 Bandmate MCP Server. Nothing to install.
upsert_list 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 upsert_list 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 upsert_list. 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.
upsert_list is provided by the Bandmate MCP Server MCP server (jnicolasgomez/bandmate-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 →