AI agents invoke load_bonus_tool to trigger actions in MCP TypeScript Starter. 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 dynamically registers new tools at runtime, which is an execution-level operation that modifies the running MCP server's capabilities. Misuse could allow an AI agent to inject arbitrary or malicious tools into the server, expanding the attack surface significantly. This is more than a simple write because it affects server behavior and execution environment, not just stored data.
From the tool's definition Dynamically register a new bonus tool
Documented attack patterns abuse exactly the kind of access load_bonus_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP TypeScript Starter, and nothing reaches the server without passing your rules. This is the rule we recommend for load_bonus_tool:
{
"version": "1",
"default": "deny",
"tools": {
"load_bonus_tool": {
"limits": [
{
"counter": "load_bonus_tool_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}load_bonus_tool 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.
Dynamically register a new bonus tool. It is categorised as a Execute tool in the MCP TypeScript Starter MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP TypeScript Starter MCP server in PolicyLayer and add a rule for load_bonus_tool: 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 MCP TypeScript Starter. Nothing to install.
load_bonus_tool 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 load_bonus_tool 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 load_bonus_tool. 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.
load_bonus_tool is provided by the MCP TypeScript Starter MCP server (sammorrowdrums/mcp-typescript-starter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP TypeScript Starter, 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.
8 MCP TypeScript Starter tools catalogued and risk-classified — across an index of 43,000+ MCP servers.