AI agents call obsidian_topic_stats 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 reports statistics or data about topics within an Obsidian vault. It has no side effects—it only queries and returns information. While the description is incomplete ('every topic the MCP' appears cut off), the core semantic ('Returns') clearly positions this as a read operation.
From the tool's definition Tool returns/queries the 'persistent topic store' for a vault. The description indicates retrieval of existing data ('Returns the persistent topic store') with no modification, deletion, or execution of operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Returns the persistent topic store for the given vault — every topic the MCP. 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_topic_stats: 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_topic_stats 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_topic_stats 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_topic_stats. 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_topic_stats 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 →