Validate an MCP server by running the MCP handshake (initialize/initialized/tools-list). Returns health report.
AI agents invoke validate_mcp_server to trigger actions in Cursor MCP Installer. 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 actively runs a protocol handshake sequence against an MCP server, which constitutes executing external operations (initialize, initialized, tools-list calls). It is not merely reading static data — it triggers live network interactions with an external server.
From the tool's definition 'Validate an MCP server by running the MCP handshake (initialize/initialized/tools-list)'
Documented attack patterns abuse exactly the kind of access validate_mcp_server gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cursor MCP Installer, and nothing reaches the server without passing your rules. This is the rule we recommend for validate_mcp_server:
{
"version": "1",
"default": "deny",
"tools": {
"validate_mcp_server": {
"limits": [
{
"counter": "validate_mcp_server_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}validate_mcp_server 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.
Validate an MCP server by running the MCP handshake (initialize/initialized/tools-list). Returns health report. It is categorised as a Execute tool in the Cursor MCP Installer MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cursor MCP Installer MCP server in PolicyLayer and add a rule for validate_mcp_server: 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 Cursor MCP Installer. Nothing to install.
validate_mcp_server 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 validate_mcp_server 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 validate_mcp_server. 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.
validate_mcp_server is provided by the Cursor MCP Installer MCP server (matthewdcage/cursor-mcp-installer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cursor MCP Installer, 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.
3 Cursor MCP Installer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.