Change the priority of an inbox item by moving it to a different section
AI agents use inbox_prioritize to create or update resources in Mcp Obsidian Planner — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Obsidian Planner environment.
This tool modifies the position/priority of an existing inbox item by moving it between sections. It is a reversible write operation — the item can be moved back. No code is executed, no data is deleted, and no financial transactions occur. Blast radius is low as it only affects task prioritization within a personal planning vault.
From the tool's definition Change the priority of an inbox item by moving it to a different section
Attacks that exploit this kind of access
Change the priority of an inbox item by moving it to a different section. It is categorised as a Write tool in the Mcp Obsidian Planner MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Obsidian Planner MCP server in PolicyLayer and add a rule for inbox_prioritize: 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 Planner. Nothing to install.
inbox_prioritize is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the inbox_prioritize 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 inbox_prioritize. 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.
inbox_prioritize is provided by the Mcp Obsidian Planner MCP server (jarero321/mcp-obsidian-planner). 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 →