lintai docs

Appearance

Rule Reference

SEC398lintai-ai-securitygovernancehardeningstablejsonwarn

MCP config: wildcard capabilities

MCP configuration grants all capabilities with `capabilities: ["*"]` or `capabilities: "*"`

Public lane
governance
Category
hardening
Provider
lintai-ai-security
Scope
per-file
Surface
json
Tier
stable
Severity
warn
Confidence
high
Detection
structural
Remediation
message only
How to read this lane

Shared authority and workflow policy review.

How to read this category

Least-privilege, provenance, or operational hygiene signal.

Activation Model

Preset Activation

These presets explain where this rule appears in the product experience.

governancesidecar lane
mcpsurface preset

Lifecycle

Stable Lifecycle Contract

State

stable

Graduation rationale

Matches explicit wildcard capability grants in MCP config.

Deterministic signal basis

JsonSignals exact wildcard detection for `capabilities` scalar or array values on parsed MCP configuration.

Malicious corpus
mcp-capabilities-wildcard
Benign corpus
mcp-capabilities-scoped-safe
structured evidence required remediation reviewed
Canonical note

Structural stable rule intended as a high-precision check with deterministic evidence.

Nearby Signals

Related Rules

SEC303MCP config: credential env passthroughMCP configuration passes through credential environment variablesgovernancehardeningjson
SEC394MCP config: wildcard auto-approveMCP configuration auto-approves all tools with `autoApprove: ["*"]`governancehardeningjson
SEC395MCP config: autoApproveTools trueMCP configuration auto-approves all tools with `autoApproveTools: true`governancehardeningjson
SEC396MCP config: trustTools trueMCP configuration fully trusts tools with `trustTools: true`governancehardeningjson
SEC397MCP config: sandbox disabledMCP configuration disables sandboxing with `sandbox: false` or `disableSandbox: true`governancehardeningjson
SEC546MCP config: Bash(*) auto-approveMCP configuration auto-approves blanket shell execution with `autoApprove: ["Bash(*)"]`governancehardeningjson

SEC398 / MCP-CAPABILITIES-WILDCARD ​

SEC398 flags MCP client configuration that grants all capabilities through capabilities: ["*"] or capabilities: "*".

Why It Matters ​

Wildcard capability grants remove a clear least-privilege boundary in shared MCP config. They make it harder to review what a committed server entry is actually allowed to do and easier for broad access to spread unnoticed.

Trigger Shape ​

The rule triggers only when all of these are true:

  • the file is a detected MCP config surface
  • the path is not fixture-like
  • capabilities is either the exact string "*"
  • or capabilities is an array containing the exact string "*"

Clean Cases ​

These stay clean:

  • capabilities: ["tools", "resources"]
  • MCP configs that omit capabilities
  • fixture-like examples under test or fixture paths

Example Trigger ​

json
{
  "mcpServers": {
    "demo": {
      "command": "node",
      "args": ["server.js"],
      "capabilities": ["*"]
    }
  }
}

Safer Example ​

json
{
  "mcpServers": {
    "demo": {
      "command": "node",
      "args": ["server.js"],
      "capabilities": ["tools", "resources"]
    }
  }
}

How To Fix ​

Replace wildcard capabilities with only the narrowly reviewed MCP capabilities that are actually required.