AI agents call obsidian_dev_errors to retrieve information from Obsidian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries diagnostic information from Obsidian's DevTools console. While error logs may contain sensitive information about the user's system, plugins, or workflows, the operation itself is non-destructive and performs no writes, deletions, or external side effects. It falls clearly into the Read category.
From the tool's definition Tool retrieves recent JS errors from the Obsidian DevTools console with no side effects or modifications. The name and description indicate a query/retrieval function: 'Returns recent JS errors' is fundamentally a read operation.
Attacks that exploit this kind of access
Returns recent JS errors from the Obsidian DevTools console. It is categorised as a Read tool in the Obsidian MCP Server, which means it retrieves data without modifying state.
Register the Obsidian MCP server in PolicyLayer and add a rule for obsidian_dev_errors: 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_dev_errors 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 obsidian_dev_errors 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_dev_errors. 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_dev_errors 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 →