Get all notes that have the specified tag.
AI agents call get_notes_by_tag 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 and retrieves existing data (notes filtered by tag) without creating, modifying, deleting, or executing any operations. It is a simple read-only lookup function typical of documentation or knowledge base systems. The low severity reflects minimal risk even if misused by an AI agent, as it only exposes information already accessible within the user's own Obsidian vault.
From the tool's definition Tool name 'get_notes_by_tag' and description 'Get all notes that have the specified tag' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get all notes that have the specified tag. 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 get_notes_by_tag: 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.
get_notes_by_tag 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 get_notes_by_tag 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 get_notes_by_tag. 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.
get_notes_by_tag 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 →