AI agents call obsidian_version 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 simply retrieves and returns the version of the Obsidian CLI binary. It performs no writes, deletions, execution of arbitrary code, or financial transactions. It is a straightforward informational query that carries minimal risk if misused by an AI agent, as an agent cannot cause harm by learning what version of software is in use.
From the tool's definition The tool 'obsidian_version' returns version information, which is a pure query operation with no side effects or data modification.
Attacks that exploit this kind of access
Returns the version of the Obsidian CLI binary in use. 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 obsidian_version: 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.
obsidian_version 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 obsidian_version 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 obsidian_version. 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.
obsidian_version is provided by the Obsidian MCP server (yuchi-chang/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 →