AI agents call list_watches to retrieve information from TalkDB without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information about existing watches (scheduled queries/alerts) and their execution history. It performs a read-only query operation with no capability to create, modify, delete, or execute any actions. The blast radius of misuse is minimal—an agent could only gain visibility into monitoring configurations, not alter them or cause harm through database operations.
From the tool's definition Tool description states 'List all watches and their last-run status.' The verb 'list' indicates data retrieval with no modification or side effects.
Attacks that exploit this kind of access
List all watches and their last-run status. It is categorised as a Read tool in the TalkDB MCP Server, which means it retrieves data without modifying state.
Register the TalkDB MCP server in PolicyLayer and add a rule for list_watches: 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 TalkDB. Nothing to install.
list_watches 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 list_watches 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 list_watches. 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.
list_watches is provided by the TalkDB MCP server (nitin-gupta1109/talkdb). 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 →