Invoke a custom tool directly with arguments
AI agents invoke goclaw_custom_tool_invoke to trigger actions in GoClaw MCP Server. 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.
Tools that invoke or execute other tools or external operations fall into the Execute category because the blast radius depends on what tool is invoked and what arguments are supplied. While the tool itself is a wrapper, it enables execution of code and operations external to the MCP server.
From the tool's definition The tool name and description indicate it 'Invoke[s] a custom tool directly with arguments', which means it executes external operations whose effects are determined by the arguments passed.
Documented attack patterns abuse exactly the kind of access goclaw_custom_tool_invoke gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and GoClaw MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for goclaw_custom_tool_invoke:
{
"version": "1",
"default": "deny",
"tools": {
"goclaw_custom_tool_invoke": {
"limits": [
{
"counter": "goclaw_custom_tool_invoke_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}goclaw_custom_tool_invoke 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.
Invoke a custom tool directly with arguments. It is categorised as a Execute tool in the GoClaw MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GoClaw MCP Server MCP server in PolicyLayer and add a rule for goclaw_custom_tool_invoke: 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 GoClaw MCP Server. Nothing to install.
goclaw_custom_tool_invoke 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 goclaw_custom_tool_invoke 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 goclaw_custom_tool_invoke. 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.
goclaw_custom_tool_invoke is provided by the GoClaw MCP Server MCP server (nextlevelbuilder/goclaw-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from GoClaw MCP Server, 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.
66 GoClaw MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.