Set named marks at specific positions in the buffer
AI agents use vim_mark to create or update resources in Mcp Neovim Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Neovim Server environment.
Setting marks in a Neovim buffer is a write operation that modifies editor state but is fully reversible. The user can clear or change marks at any time. This is not a Read (no data retrieval), Execute (doesn't run arbitrary code), Destructive (marks can be undone), or Financial operation. The blast radius of misuse is low since marks are navigation aids with no data loss or system impact.
From the tool's definition Tool description states 'Set named marks at specific positions in the buffer' — this modifies buffer state by creating/updating marks, which is a reversible operation (marks can be cleared or moved).
Attacks that exploit this kind of access
Set named marks at specific positions in the buffer. It is categorised as a Write tool in the Mcp Neovim Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Neovim Server MCP server in PolicyLayer and add a rule for vim_mark: 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 Mcp Neovim Server. Nothing to install.
vim_mark 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 vim_mark 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 vim_mark. 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.
vim_mark is provided by the Mcp Neovim Server MCP server (mcp-neovim-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 →