Evaluate MCP Trust Boundary
evaluate_mcp_trust_boundaryEvaluate an MCP server deployment against trust-boundary best practices to flag risks in transport, authentication, input validation, read-only behavior, and shell command execution.
Instructions
Evaluates an MCP server deployment configuration against trust-boundary best practices.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"transport": "<transport>",
"isReadOnly": "<isReadOnly>",
"validatesInputs": "<validatesInputs>",
"executesShellCommands": "<executesShellCommands>",
"requiresAuthentication": "<requiresAuthentication>"
},
"name": "evaluate_mcp_trust_boundary"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| transport | Yes | Transport type: 'stdio', 'http', or 'streamable-http'. | |
| isReadOnly | Yes | True when every tool avoids external state mutations. | |
| bindAddress | No | Optional listen address when using HTTP transport (e.g. 127.0.0.1). | |
| validatesInputs | Yes | True when all tool arguments are schema-validated and canonicalized. | |
| executesShellCommands | Yes | True when any tool can invoke arbitrary OS shell commands. | |
| requiresAuthentication | Yes | True when HTTP/network transport requires caller authentication. |