Manually re-detect the available command-line search tools on the system. This is useful if you have installed a new tool (like ripgrep) after starting the server.
AI agents invoke refresh_search_tools to trigger actions in Code Index. 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 triggers an active system scan/detection process that executes system-level operations to discover installed command-line tools. It is not a passive read — it initiates a detection routine that interacts with the operating system environment. While not destructive, it executes an external operation whose effects depend on the current system state, placing it in the Execute category.
From the tool's definition Manually re-detect the available command-line search tools on the system
Documented attack patterns abuse exactly the kind of access refresh_search_tools gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code Index, and nothing reaches the server without passing your rules. This is the rule we recommend for refresh_search_tools:
{
"version": "1",
"default": "deny",
"tools": {
"refresh_search_tools": {
"limits": [
{
"counter": "refresh_search_tools_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}refresh_search_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.
Manually re-detect the available command-line search tools on the system. This is useful if you have installed a new tool (like ripgrep) after starting the server. It is categorised as a Execute tool in the Code Index MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Code Index MCP server in PolicyLayer and add a rule for refresh_search_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 Code Index. Nothing to install.
refresh_search_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 refresh_search_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 refresh_search_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.
refresh_search_tools is provided by the Code Index MCP server (johnhuang316/code-index-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Code Index, 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.
14 Code Index tools catalogued and risk-classified — across an index of 43,000+ MCP servers.