Insert or replace content at a specific line
AI agents use vault_edit_line to create or update resources in Connect MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Connect MCP environment.
This tool modifies file content reversibly by editing specific lines within vault notes. It is a Write operation because changes can be undone (typical in editors and Obsidian's undo system), and does not permanently delete data. While it could corrupt notes if misused, the reversible nature and limited scope (single-line edits) place it in Write rather than Destructive.
From the tool's definition Tool name 'vault_edit_line' and description 'Insert or replace content at a specific line' directly indicate modification of existing note content.
Attacks that exploit this kind of access
Insert or replace content at a specific line. It is categorised as a Write tool in the Connect MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Connect MCP server in PolicyLayer and add a rule for vault_edit_line: 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 Connect MCP. Nothing to install.
vault_edit_line 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 vault_edit_line 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 vault_edit_line. 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.
vault_edit_line is provided by the Connect MCP server (joch/obsidian-connect-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 →