Open a file in the Obsidian UI
AI agents invoke open to trigger actions in Obsidian Local. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external UI operation in Obsidian (opening a file in the application interface), which constitutes an action that affects the running application's state. It's not a pure read (it changes the UI state/focus), and it executes an Obsidian internal command. Given the server description mentions 'execution of internal Obsidian commands', this fits Execute.
From the tool's definition Open a file in the Obsidian UI
Attacks that exploit this kind of access
Open a file in the Obsidian UI. It is categorised as a Execute tool in the Obsidian Local MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Obsidian Local MCP server in PolicyLayer and add a rule for open: 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 Local. Nothing to install.
open is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open 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 open. 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.
open is provided by the Obsidian Local MCP server (matthewsuazo/obsidian-local-mcp). 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 →