Analyze docker-compose.yml, split it into separate deploy units, provision known databases through Data Layer, and deploy the remaining services as separate apps. If any service uses a local Docker build, provide local_image_archives keyed by service name after building and exporting those images.
AI agents invoke deploy_compose to trigger actions in PlugLayer 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.
This tool executes arbitrary deployment operations based on user-provided docker-compose configuration. While it modifies infrastructure state (making it Write-adjacent), the core action is executing a deployment pipeline—analyzing, building, and provisioning—which fundamentally involves running external operations (Docker builds, service deployments) whose effects are contingent on input arguments.
From the tool's definition Tool deploys services, provisions databases, and executes builds. Description states it will 'deploy the remaining services as separate apps' and 'build and export' Docker images, indicating execution of infrastructure operations whose effects depend on the…
Attacks that exploit this kind of access
Analyze docker-compose.yml, split it into separate deploy units, provision known databases through Data Layer, and deploy the remaining services as separate apps. If any service uses a local Docker build, provide local_image_archives keyed by service name after building and exporting those images. It is categorised as a Execute tool in the PlugLayer MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PlugLayer MCP Server MCP server in PolicyLayer and add a rule for deploy_compose: 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 PlugLayer MCP Server. Nothing to install.
deploy_compose 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 deploy_compose 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 deploy_compose. 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.
deploy_compose is provided by the PlugLayer MCP Server MCP server (pluglayer/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 →