Semantic search across the curated Obsidian vault. Use this
AI agents call obsidian_search 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 information from an Obsidian vault without modifying, executing, or deleting anything. It is a pure Read operation with minimal security risk, hence low severity. The explicit mention of 'read-only' in the server description provides high confidence.
From the tool's definition Tool description explicitly states 'Semantic search across the curated Obsidian vault' and server description emphasizes 'read-only semantic search'.
Attacks that exploit this kind of access
Semantic search across the curated Obsidian vault. 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_search: 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_search 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_search 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_search. 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_search 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 →