Send a reply back to an agent on the switchboard bus.
AI agents use reply 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 tool sends messages to other agents, which creates new data records in the switchboard system. While communication itself is relatively benign, misuse could enable social engineering, misinformation injection, or coordination of malicious actions across multiple agents.
From the tool's definition Tool name 'reply' combined with description 'Send a reply back to an agent on the switchboard bus' indicates creation/modification of message data on a communication bus.
Attacks that exploit this kind of access
Send a reply back to an agent on the switchboard bus. 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 reply: 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.
reply 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 reply 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 reply. 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.
reply 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 →