Execute a command in a running deployment
AI agents invoke exec to trigger actions in Koyeb 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 runs arbitrary commands within a deployed container or instance, which is a classic Execute category action. The blast radius is high because arbitrary command execution on production deployments could compromise data, availability, or security. While not immediately destructive (unless the executed command itself is), the capability to run any command makes this Execute rather than Write.
From the tool's definition Tool name 'exec' with description 'Execute a command in a running deployment' directly indicates code/command execution capability on active infrastructure.
Attacks that exploit this kind of access
Execute a command in a running deployment. It is categorised as a Execute tool in the Koyeb MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Koyeb MCP Server MCP server in PolicyLayer and add a rule for exec: 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 Koyeb MCP Server. Nothing to install.
exec 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 exec 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 exec. 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.
exec is provided by the Koyeb MCP Server MCP server (samihalawa/mcp-server-koyeb). 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 →