Read a single note whole, straight from disk. Use this
AI agents call obsidian_read 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 note content from an Obsidian vault without creating, modifying, or deleting data. It produces no side effects beyond information disclosure. The server description confirms a 'read-only semantic search' workflow. Risk is minimal since the tool only accesses existing data.
From the tool's definition Tool name 'obsidian_read' combined with description 'Read a single note whole, straight from disk' explicitly indicates a retrieval operation with no modification capabilities.
Attacks that exploit this kind of access
Read a single note whole, straight from disk. Use this. 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_read: 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_read 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_read 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_read. 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_read 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 →