Get incremental stdout/stderr from the running watch.
AI agents call tdd_get_watch_changes to retrieve information from Promethean OS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns accumulated output from a watch process. It is a passive read operation that retrieves information already generated by an external process. It does not execute code, modify data, delete anything, or incur financial obligations.
From the tool's definition 'Get incremental stdout/stderr from the running watch' — retrieves output data without modifying state or triggering side effects.
Attacks that exploit this kind of access
Get incremental stdout/stderr from the running watch. It is categorised as a Read tool in the Promethean OS MCP MCP Server, which means it retrieves data without modifying state.
Register the Promethean OS MCP server in PolicyLayer and add a rule for tdd_get_watch_changes: 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 Promethean OS MCP. Nothing to install.
tdd_get_watch_changes 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 tdd_get_watch_changes 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 tdd_get_watch_changes. 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.
tdd_get_watch_changes is provided by the Promethean OS MCP server (octave-commons/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 →