Detects operating system and environment information
AI agents call os_detect to retrieve information from Mcp Ssh Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system information (OS type, environment details) for query purposes. It performs passive detection/reporting only, with no capability to modify systems, execute commands, delete data, or initiate financial transactions. The minimal information disclosure risk (OS fingerprinting) is typical for Read operations and warrants low severity.
From the tool's definition Tool name 'os_detect' and description 'Detects operating system and environment information' indicate information retrieval with no side effects. No data modification, deletion, or external action execution is implied.
Attacks that exploit this kind of access
Detects operating system and environment information. It is categorised as a Read tool in the Mcp Ssh Tool MCP Server, which means it retrieves data without modifying state.
Register the Mcp Ssh Tool MCP server in PolicyLayer and add a rule for os_detect: 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 Tool. Nothing to install.
os_detect 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 os_detect 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 os_detect. 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.
os_detect is provided by the Mcp Ssh Tool MCP server (skot/mcp-ssh-tool). 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 →