AI agents call health-check to retrieve information from MCP Codebase Insight without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Health checks are read-only operations that query the current status of a service. They have no side effects, do not execute arbitrary code, do not modify data, and do not create financial obligations. The blast radius of misuse is minimal—an attacker could learn the server is running, but cannot leverage this tool alone to cause harm.
From the tool's definition Tool name is 'health-check' and description states 'Check server health status' — this retrieves diagnostic information about the server's operational state without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access health-check gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Codebase Insight, and nothing reaches the server without passing your rules. This is the rule we recommend for health-check:
{
"version": "1",
"default": "deny",
"tools": {
"health-check": {}
}
}health-check is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check server health status. It is categorised as a Read tool in the MCP Codebase Insight MCP Server, which means it retrieves data without modifying state.
Register the MCP Codebase Insight MCP server in PolicyLayer and add a rule for health-check: 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 Codebase Insight. Nothing to install.
health-check is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the health-check 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 health-check. 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.
health-check is provided by the MCP Codebase Insight MCP server (tosin2013/mcp-codebase-insight). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Codebase Insight, 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.
4 MCP Codebase Insight tools catalogued and risk-classified — across an index of 43,000+ MCP servers.