AI agents invoke reload-tools to trigger actions in MCPX MCP Gateway. 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.
Reloading tools is an operational action that triggers an external process (refreshing the tool registry or configuration), not a simple read. It could affect the availability and routing of all tools in the MCP gateway, making it an Execute-category action. Misuse could disrupt agentic workflows by causing unexpected tool reconfigurations. Confidence is moderate because the description is minimal.
From the tool's definition "reloads tools" - triggers a reload/refresh operation on the tool registry
Documented attack patterns abuse exactly the kind of access reload-tools gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCPX MCP Gateway, and nothing reaches the server without passing your rules. This is the rule we recommend for reload-tools:
{
"version": "1",
"default": "deny",
"tools": {
"reload-tools": {
"limits": [
{
"counter": "reload-tools_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}reload-tools 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.
reloads tools. It is categorised as a Execute tool in the MCPX MCP Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCPX MCP Gateway MCP server in PolicyLayer and add a rule for reload-tools: 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 MCPX MCP Gateway. Nothing to install.
reload-tools 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 reload-tools 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 reload-tools. 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.
reload-tools is provided by the MCPX MCP Gateway MCP server (thelunarcompany/lunar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 MCPX MCP Gateway tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 MCPX MCP Gateway tools catalogued and risk-classified — across an index of 42,500+ MCP servers.