Skip to content

Rule Reference

SEC567lintai-ai-securitystablejsonwarn

MCP config: Read wildcard auto-approve

MCP configuration auto-approves `Read(*)` through `autoApprove`

Provider
lintai-ai-security
Surface
json
Scope
per_file
Tier
stable
Severity
warn
Confidence
high
Detection
structural
Remediation
message_only

Activation Model

Preset Membership

This rule is part of the builtin activation graph through these preset memberships.

Lifecycle

Stable Lifecycle Contract

State

stable_gated

Graduation rationale

Matches explicit `Read(*)` auto-approval in MCP client config.

Deterministic signal basis

JsonSignals exact array-item detection for `autoApprove: ["Read(*)"]` on parsed MCP configuration.

Malicious corpus
mcp-autoapprove-wildcard-tool-family
Benign corpus
mcp-autoapprove-wildcard-tool-family-specific-safe
structured evidence required remediation reviewed
Canonical note

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

Nearby Signals

Related Rules

SEC567 / MCP-AUTOAPPROVE-READ-WILDCARD

SEC567 flags MCP configuration when autoApprove includes the exact tool token Read(*).

Why It Matters

autoApprove removes the normal review boundary for named MCP tools. Read(*) grants unconstrained repository and filesystem reading, so auto-approving it weakens least-privilege expectations for shared MCP clients.

Trigger Shape

  • the file is a detected MCP configuration surface
  • autoApprove is a string array
  • the array contains the exact item Read(*)

How To Fix

Remove Read(*) from autoApprove and replace it with narrower reviewed read scopes where possible.