Echo tool that returns user-provided information as-is
AI agents call echo_message to retrieve information from Dev Tool MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure echo/reflection function that reads input and outputs it without modification or side effects. It has no capability to access external data, modify state, or trigger operations. While it exists on a dev tool server with web crawling capabilities, the tool itself performs only a read operation (reflecting input).
From the tool's definition The tool 'echo_message' simply returns user-provided information as-is with no side effects. The description contains no indication of any modification, deletion, execution, or financial operations.
Attacks that exploit this kind of access
Echo tool that returns user-provided information as-is. It is categorised as a Read tool in the Dev Tool MCP MCP Server, which means it retrieves data without modifying state.
Register the Dev Tool MCP server in PolicyLayer and add a rule for echo_message: 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 Dev Tool MCP. Nothing to install.
echo_message 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 echo_message 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 echo_message. 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.
echo_message is provided by the Dev Tool MCP server (osins/dev-tool-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 →