Format the current buffer or an explicit target through the headless Neovim runtime without saving. useLatestChangedTick is current-buffer-only; useLatestSessionChangedTick works for explicit path targets or already-open explicit bufferId targets in the editor session.
AI agents use format_buffer to create or update resources in Vigentic MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Vigentic MCP environment.
Formatting is a reversible modification operation that alters file content in memory. While non-destructive and not permanent until saved, it materially changes data and can affect code structure. This is Write rather than Execute because it applies automated formatting rules rather than executing arbitrary code.
From the tool's definition "Format the current buffer or an explicit target through the headless Neovim runtime without saving." The tool modifies buffer contents (formatting), creating new state that persists in the editor session until explicitly saved.
Attacks that exploit this kind of access
Format the current buffer or an explicit target through the headless Neovim runtime without saving. useLatestChangedTick is current-buffer-only; useLatestSessionChangedTick works for explicit path targets or already-open explicit bufferId targets in the editor session. It is categorised as a Write tool in the Vigentic MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Vigentic MCP server in PolicyLayer and add a rule for format_buffer: 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 Vigentic MCP. Nothing to install.
format_buffer 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 format_buffer 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 format_buffer. 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.
format_buffer is provided by the Vigentic MCP server (munozu/vigentic-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 →