Start HTTP web server for icon search and selection interface
AI agents invoke start_web_server to trigger actions in Icon. 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 executes code to start a web server process, which is a system-level operation. While not destructive, it initiates external processes whose effects depend on execution context. The high severity reflects that an uncontrolled agent could start multiple web servers, consume resources, expose services unintentionally, or interfere with existing network operations.
From the tool's definition Tool performs an action that triggers external operations with side effects: 'Start HTTP web server' indicates launching a network service, which is a command execution that cannot be simply reversed without explicit stopping.
Documented attack patterns abuse exactly the kind of access start_web_server gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Icon, and nothing reaches the server without passing your rules. This is the rule we recommend for start_web_server:
{
"version": "1",
"default": "deny",
"tools": {
"start_web_server": {
"limits": [
{
"counter": "start_web_server_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}start_web_server 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.
Free to start. No card required.
Start HTTP web server for icon search and selection interface. It is categorised as a Execute tool in the Icon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Icon MCP server in PolicyLayer and add a rule for start_web_server: 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 Icon. Nothing to install.
start_web_server 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 start_web_server 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 start_web_server. 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.
start_web_server is provided by the Icon MCP server (liliangshan/mcp-server-icon). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Icon, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Icon tools catalogued and risk-classified — across an index of 43,000+ MCP servers.