turbo
Runs Turborepo tasks and returns structured per-package results with cache hit/miss info.
This record as markdown: /tools/io-github-dave-london-build/turbo.md
What turbo does on Build
AI agents invoke turbo to trigger actions in Build. 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 turbo is rated High
The tool runs Turborepo tasks, which means it executes arbitrary build scripts, test commands, or other pipeline tasks defined in the monorepo. This is an Execute-category action with high severity because it can trigger arbitrary code execution across multiple packages, and the scope (per-package results) implies potentially wide blast radius in a monorepo context.
From the tool's definition 'Runs Turborepo tasks' — actively executes build/task runner commands across packages
Attacks that exploit this kind of access
The rule that runs turbo safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Build, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For turbo, this is the rule to start with:
turbo 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 Build, apply this rule, and every turbo call is checked against it from then on.
Questions about turbo
Runs Turborepo tasks and returns structured per-package results with cache hit/miss info. It is categorised as a Execute tool in the Build MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Build MCP server in PolicyLayer and add a rule for turbo: 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 Build. Nothing to install.
turbo 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 turbo 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 turbo. 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.
turbo is provided by the Build MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Build, and thousands of servers like it.
Across the catalogue