Self-report current activity (awareness layer), e.g. activity=
AI agents use set_status to create or update resources in Mcp Switchboard — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Switchboard environment.
This is a Write operation: it creates or updates agent status metadata in the switchboard's awareness layer. The effect is reversible and has no side effects beyond recording the agent's self-reported state. It does not execute code, delete data, move funds, or trigger external operations.
From the tool's definition Tool name 'set_status' and description indicate it modifies agent status/awareness metadata via self-report ('Self-report current activity').
Attacks that exploit this kind of access
Self-report current activity (awareness layer), e.g. activity=. It is categorised as a Write tool in the Mcp Switchboard MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Switchboard MCP server in PolicyLayer and add a rule for set_status: 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 Mcp Switchboard. Nothing to install.
set_status 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 set_status 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 set_status. 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.
set_status is provided by the Mcp Switchboard MCP server (jemplayer82/mcp-switchboard). 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 →