Basic vector search across vault chunks using ChromaDB.
AI agents call search_notes to retrieve information from Graph Rag Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries an existing knowledge base (ChromaDB vector store) and returns search results. It has no side effects, cannot modify data, execute code, or affect external systems. The blast radius of misuse is minimal—an agent could retrieve sensitive information from the Obsidian vault, but cannot alter or delete it. Classified as Read (retrieval) with low severity.
From the tool's definition Tool performs 'vector search across vault chunks using ChromaDB' — a retrieval operation with no modification, deletion, or execution of external systems.
Attacks that exploit this kind of access
Basic vector search across vault chunks using ChromaDB. It is categorised as a Read tool in the Graph Rag Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Graph Rag Obsidian MCP server in PolicyLayer and add a rule for search_notes: 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 Graph Rag Obsidian. Nothing to install.
search_notes 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 search_notes 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 search_notes. 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.
search_notes is provided by the Graph Rag Obsidian MCP server (nickshffer/graph-rag-mcp-server). 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 →