Export all notes to a JSON backup file and return the path.
AI agents call index-backup to retrieve information from MCP Index Notes without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads all notes and exports them to a JSON file. It creates a file on disk (which is a write-side-effect), but its primary purpose is data retrieval/backup rather than modifying application data. However, writing a file to disk means it has a side effect beyond pure read — but this is reversible and common for backups. The most severe applicable category is Write, since it creates a new file.
From the tool's definition Export all notes to a JSON backup file and return the path
Attacks that exploit this kind of access
Export all notes to a JSON backup file and return the path. It is categorised as a Read tool in the MCP Index Notes MCP Server, which means it retrieves data without modifying state.
Register the MCP Index Notes MCP server in PolicyLayer and add a rule for index-backup: 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 Index Notes. Nothing to install.
index-backup 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 index-backup 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 index-backup. 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.
index-backup is provided by the MCP Index Notes MCP server (vjsr007/mcp-index-notes). 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 →