esbuild
Runs the esbuild bundler and returns structured errors, warnings, and output files.
This record as markdown: /tools/io-github-dave-london-build/esbuild.md
What esbuild does on Build
AI agents invoke esbuild 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 esbuild is rated High
The tool runs an external command (esbuild) which bundles code, executes arbitrary build configurations, and produces output files. This is an Execute-category action with high severity since a misused bundler invocation could process malicious code, exfiltrate source files, or produce compromised build artifacts.
From the tool's definition 'Runs the esbuild bundler' — explicitly executes an external build/bundling process
Attacks that exploit this kind of access
The rule that runs esbuild 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 esbuild, this is the rule to start with:
esbuild 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 esbuild call is checked against it from then on.
Questions about esbuild
Runs the esbuild bundler and returns structured errors, warnings, and output files. 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 esbuild: 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.
esbuild 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 esbuild 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 esbuild. 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.
esbuild 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