Open graph view in Obsidian (requires REST API plugin)
AI agents invoke open_graph to trigger actions in Obsidian MCP Server. 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 a UI action in Obsidian (opening the graph view), which is an external operation whose effect is executing a command in the application. It does not read, write, or delete data, but it does trigger an external operation. The severity is low because it merely changes the UI state with no data modification or destruction.
From the tool's definition 'Open graph view in Obsidian' - triggers an external UI operation in the Obsidian application
Attacks that exploit this kind of access
Open graph view in Obsidian (requires REST API plugin). It is categorised as a Execute tool in the Obsidian MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Obsidian MCP Server MCP server in PolicyLayer and add a rule for open_graph: 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 Server. Nothing to install.
open_graph 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_graph 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_graph. 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_graph is provided by the Obsidian MCP Server MCP server (victors081/obsidian-mcp-server). 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 →