build-shell
Build an HTML shell with CSP, data injection, and optional bridge runtime
This record as markdown: /tools/frontmcp/build-shell.md
What build-shell does on Frontmcp
AI agents invoke build-shell to trigger actions in Frontmcp. 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 build-shell is rated High
This tool generates executable HTML output with dynamic data injection and runtime bridging capabilities. While not destructive by itself, the ability to build and inject code into HTML shells with runtime execution context qualifies as Execute-category risk. An AI agent could misuse this to generate malicious HTML payloads, inject untrusted data, or create bridge connections to unintended services.
From the tool's definition Tool name is 'build-shell' and description states it 'Build[s] an HTML shell with CSP, data injection, and optional bridge runtime'.
Attacks that exploit this kind of access
The rule that runs build-shell safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Frontmcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For build-shell, this is the rule to start with:
build-shell 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 Frontmcp, apply this rule, and every build-shell call is checked against it from then on.
Questions about build-shell
Build an HTML shell with CSP, data injection, and optional bridge runtime. It is categorised as a Execute tool in the Frontmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Front MCP server in PolicyLayer and add a rule for build-shell: 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 Frontmcp. Nothing to install.
build-shell 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 build-shell 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 build-shell. 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.
build-shell is provided by the Front MCP server (agentfront/frontmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Front, and thousands of servers like it.
Across the catalogue