Return vault stats, the fresh _index.md, and the OBSIDIAN
AI agents call obsidian_overview to retrieve information from Second Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries vault information without side effects. It reads vault statistics and existing documentation (index.md), which are informational operations typical of the Read category. The low severity reflects that vault metadata and statistics pose minimal risk if misused by an agent—they cannot modify the vault, trigger external operations, or cause irreversible harm.
From the tool's definition Tool returns vault statistics and index metadata. The description indicates it retrieves data ('Return vault stats, the fresh _index.md') with no indication of modification, deletion, or execution.
Attacks that exploit this kind of access
Return vault stats, the fresh _index.md, and the OBSIDIAN. It is categorised as a Read tool in the Second Brain MCP Server, which means it retrieves data without modifying state.
Register the Second Brain MCP server in PolicyLayer and add a rule for obsidian_overview: 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 Second Brain. Nothing to install.
obsidian_overview 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_overview 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_overview. 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_overview is provided by the Second Brain MCP server (noesskeetit/second-brain-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 →