Connect to a project via SSH. (provides command for interactive terminal)
AI agents invoke mittwald_project_ssh to trigger actions in Mittwald MCP Server. 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.
Establishing an SSH connection and providing an interactive terminal allows execution of arbitrary commands on the remote project environment. This is an Execute-category action with high severity since an AI agent could run destructive or unauthorized commands on the server through this terminal access.
From the tool's definition Connect to a project via SSH. (provides command for interactive terminal)
Attacks that exploit this kind of access
Connect to a project via SSH. (provides command for interactive terminal). It is categorised as a Execute tool in the Mittwald MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mittwald MCP Server MCP server in PolicyLayer and add a rule for mittwald_project_ssh: 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 Mittwald MCP Server. Nothing to install.
mittwald_project_ssh 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 mittwald_project_ssh 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 mittwald_project_ssh. 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.
mittwald_project_ssh is provided by the Mittwald MCP Server MCP server (mittwald/mcp-server). 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 →