AI agents call list_commands to retrieve information from Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates available commands without executing them, triggering them, or modifying any data. It is purely informational and defensive (helps an agent understand available actions before taking them). The blast radius of misuse is minimal—listing commands poses no direct harm.
From the tool's definition Tool name 'list_commands' and description 'List every registered Obsidian command' indicates a query/retrieval operation with no data modification or execution of those commands.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
List every registered Obsidian command (built-in + plugin) with its id and human name. Use this before. It is categorised as a Read tool in the Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP server in PolicyLayer and add a rule for list_commands: 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 Obsidian. Nothing to install.
list_commands 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 list_commands 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 list_commands. 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.
list_commands is provided by the Obsidian MCP server (yanxue06/obsidian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →