Find and replace text inside an Obsidian note using eval with app.vault.read/modify
AI agents use replace to create or update resources in Obsidian Local — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obsidian Local environment.
This tool modifies note content reversibly through search-and-replace operations. While it changes existing data, it does not permanently delete or destroy information (Destructive), nor does it execute arbitrary code (Execute). It fits Write category as it updates/modifies content.
From the tool's definition Tool description explicitly states it performs 'find and replace text inside an Obsidian note' and uses 'app.vault.read/modify'. The 'modify' operation and the nature of replacing content confirms data modification capability.
Attacks that exploit this kind of access
Find and replace text inside an Obsidian note using eval with app.vault.read/modify. It is categorised as a Write tool in the Obsidian Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obsidian Local MCP server in PolicyLayer and add a rule for replace: 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.
replace 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 replace 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 replace. 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.
replace 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 →