AI agents invoke open_path to trigger actions in Sysprobe. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes xdg-open which launches an external application or handler. The effects depend on what path/URL is passed — it could open a browser, run a document viewer, or trigger other applications. This is an Execute-category action since it triggers external operations whose effects depend on arguments, not merely reading or writing data directly.
From the tool's definition Open a file/folder/URL with the default handler (xdg-open)
Attacks that exploit this kind of access
[ACTION] Open a file/folder/URL with the default handler (xdg-open). It is categorised as a Execute tool in the Sysprobe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sysprobe MCP server in PolicyLayer and add a rule for open_path: 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 Sysprobe. Nothing to install.
open_path is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open_path 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 open_path. 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.
open_path is provided by the Sysprobe MCP server (raindancer118/sysprobe-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 →