This record as markdown: /tools/mittwald-mcp-server/mittwald-app-ssh.md
What mittwald_app_ssh does on Mittwald MCP Server
AI agents invoke mittwald_app_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.
Why mittwald_app_ssh is rated High
SSH access allows arbitrary command execution on the remote server. An AI agent misusing this tool could run any shell commands, exfiltrate data, modify files, install malware, or cause complete system compromise. This is the highest-risk Execute-category action with critical blast radius.
From the tool's definition Connect to an app via SSH
Attacks that exploit this kind of access
The rule that runs mittwald_app_ssh safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Mittwald MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For mittwald_app_ssh, this is the rule to start with:
mittwald_app_ssh stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Mittwald MCP Server, apply this rule, and every mittwald_app_ssh call is checked against it from then on.
Questions about mittwald_app_ssh
Connect to an app via SSH. 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_app_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_app_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_app_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_app_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_app_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.
More on Mittwald MCP Server, and thousands of servers like it.
Across the catalogue