Manage persistent watch expressions
AI agents use manage-watch-expressions to create or update resources in Debugger MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Debugger MCP Server environment.
'Manage' implies creating, updating, or deleting watch expressions stored persistently. This is a Write-level operation as it modifies stored configuration/state (watch expressions) in the debugger. While deletion could occur, 'manage' broadly covers CRUD operations on watch expressions, and since these are debugger-side configurations rather than application data, the blast radius is medium at most.
From the tool's definition Manage persistent watch expressions
Attacks that exploit this kind of access
Manage persistent watch expressions. It is categorised as a Write tool in the Debugger MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Debugger MCP Server MCP server in PolicyLayer and add a rule for manage-watch-expressions: 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 Debugger MCP Server. Nothing to install.
manage-watch-expressions 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 manage-watch-expressions 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 manage-watch-expressions. 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.
manage-watch-expressions is provided by the Debugger MCP Server MCP server (phoenixrr2113/debugger-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 →