fe_build
Запустить npm-скрипт (build/dev).
This record as markdown: /tools/llm-agent-sniffer-integration/fe-build.md
What fe_build does on Llm Agent Sniffer Integration
AI agents invoke fe_build to trigger actions in Llm Agent Sniffer Integration. 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 fe_build is rated High
fe_build triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs fe_build safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Llm Agent Sniffer Integration, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For fe_build, this is the rule to start with:
fe_build 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 Llm Agent Sniffer Integration, apply this rule, and every fe_build call is checked against it from then on.
Questions about fe_build
Запустить npm-скрипт (build/dev). It is categorised as a Execute tool in the Llm Agent Sniffer Integration MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Llm Agent Sniffer Integration MCP server in PolicyLayer and add a rule for fe_build: 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 Llm Agent Sniffer Integration. Nothing to install.
fe_build 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 fe_build 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 fe_build. 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.
fe_build is provided by the Llm Agent Sniffer Integration MCP server (mobstardos/llm-agent-sniffer-integration). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Llm Agent Sniffer Integration, and thousands of servers like it.
Across the catalogue