测试服务器连接
AI agents call test_connection to retrieve information from MCP SSH Tools Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Testing a connection is a read-only diagnostic operation that checks reachability without modifying state, executing commands, or transferring data. However, the description is minimal (only in Chinese, meaning 'test server connection'), so there is some uncertainty about whether it has side effects beyond probing connectivity.
From the tool's definition '测试服务器连接' (test server connection) — the tool tests/verifies a connection, which is a read/probe operation with no apparent side effects.
Attacks that exploit this kind of access
测试服务器连接. It is categorised as a Read tool in the MCP SSH Tools Server MCP Server, which means it retrieves data without modifying state.
Register the MCP SSH Tools Server MCP server in PolicyLayer and add a rule for test_connection: 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 SSH Tools Server. Nothing to install.
test_connection 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 test_connection 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 test_connection. 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.
test_connection is provided by the MCP SSH Tools Server MCP server (nwnusun-cool/mcp-server-ssh-tools). 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 →