Deploy a docker-compose compatible file to a Mittwald stack.
AI agents invoke mittwald_stack_deploy 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.
Deploying docker-compose files executes containerized code and modifies infrastructure state. While not immediately destructive (containers can be stopped), the deployment triggers external operations that cannot be fully controlled or predicted without inspecting the compose file.
From the tool's definition Tool name 'mittwald_stack_deploy' and description 'Deploy a docker-compose compatible file to a Mittwald stack' indicate execution of containerized workloads.
Attacks that exploit this kind of access
Deploy a docker-compose compatible file to a Mittwald stack. 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_stack_deploy: 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_stack_deploy 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_stack_deploy 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_stack_deploy. 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_stack_deploy 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 →