AI agents invoke obsidian_reload_plugin to trigger actions in Obsidian. 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.
Reloading a plugin restarts its execution lifecycle, which can trigger side effects depending on the plugin's initialization code. This is an external operation with execution semantics rather than a simple read or write. Misuse could cause instability or trigger unintended plugin behavior, but the blast radius is moderate since it affects only a single plugin in a local Obsidian instance.
From the tool's definition "Reloads a plugin" — triggers an external operation (plugin reload) on a running Obsidian instance
Attacks that exploit this kind of access
Reloads a plugin. It is categorised as a Execute tool in the Obsidian MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Obsidian MCP server in PolicyLayer and add a rule for obsidian_reload_plugin: 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. Nothing to install.
obsidian_reload_plugin 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 obsidian_reload_plugin 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 obsidian_reload_plugin. 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.
obsidian_reload_plugin is provided by the Obsidian MCP server (yuchi-chang/obsidian-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 →