AI agents call read_note to retrieve information from Obsidian MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries existing note content without creating, modifying, or deleting data. It has no side effects beyond information disclosure. While the Obsidian server overall supports destructive operations (delete_note, update_note), this specific tool is limited to read-only access, making it a low-severity Read category tool.
From the tool's definition Tool name is 'read_note' and description states 'Read the content of a note in the Obsidian vault' - a pure retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access read_note gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for read_note:
{
"version": "1",
"default": "deny",
"tools": {
"read_note": {}
}
}read_note is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Read the content of a note in the Obsidian vault. It is categorised as a Read tool in the Obsidian MCP MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP server in PolicyLayer and add a rule for read_note: 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 Obsidian MCP. Nothing to install.
read_note 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 read_note 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 read_note. 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.
read_note is provided by the Obsidian MCP server (newtype-01/obsidian-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Obsidian MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Obsidian MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.