connect_vps
AI agents use connect_vps to create or update resources in Mt5 Remote Reader — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mt5 Remote Reader environment.
The tool name suggests establishing a connection to a remote VPS via SSH. While this is not purely reading data, it is a setup/initialization action (Write-level) rather than destructive. However, given the empty description, confidence is low. The server context says read-only access, but connection establishment is a side-effectful operation. Severity is medium as a misused SSH connection could expose the VPS.
From the tool's definition Tool name 'connect_vps'; description is empty and uninformative.
Attacks that exploit this kind of access
connect_vps. It is categorised as a Write tool in the Mt5 Remote Reader MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mt5 Remote Reader MCP server in PolicyLayer and add a rule for connect_vps: 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 Mt5 Remote Reader. Nothing to install.
connect_vps 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 connect_vps 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 connect_vps. 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.
connect_vps is provided by the Mt5 Remote Reader MCP server (marco7734/mt5-remote-reader-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 →