List the N most recently modified notes in the vault.
AI agents call get_recent_notes to retrieve information from Mcp Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only retrieval of note metadata (recently modified notes). It has no side effects—it does not create, modify, delete, or execute operations. The blast radius of misuse is minimal; an AI could at worst discover which notes exist and their modification timestamps, which is low-sensitivity information in most vault contexts.
From the tool's definition Tool name 'get_recent_notes' and description 'List the N most recently modified notes in the vault' indicate a query operation that retrieves metadata about notes without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
List the N most recently modified notes in the vault. It is categorised as a Read tool in the Mcp Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Mcp Obsidian MCP server in PolicyLayer and add a rule for get_recent_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 Mcp Obsidian. Nothing to install.
get_recent_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 get_recent_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 get_recent_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.
get_recent_notes is provided by the Mcp Obsidian MCP server (jkang8/mcp-obsidian). 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 →