워치리스트 업데이트
AI agents use watchlist_update to create or update resources in PM-MCP (Portfolio Management MCP Server) — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PM-MCP (Portfolio Management MCP Server) environment.
This tool creates or modifies data (watchlist entries) in a reversible manner. The user can undo changes by updating the watchlist again. It does not delete data permanently, execute code, or move money, so it falls under Write rather than Destructive or Financial.
From the tool's definition watchlist_update - updates a watchlist, which modifies user data by adding, removing, or changing monitored securities.
Attacks that exploit this kind of access
워치리스트 업데이트. It is categorised as a Write tool in the PM-MCP (Portfolio Management MCP Server) MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PM-MCP (Portfolio Management MCP Server) MCP server in PolicyLayer and add a rule for watchlist_update: 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 PM-MCP (Portfolio Management MCP Server). Nothing to install.
watchlist_update 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 watchlist_update 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 watchlist_update. 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.
watchlist_update is provided by the PM-MCP (Portfolio Management MCP Server) MCP server (surplus96/pm-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 →