AI agents use lsp_format_document to create or update resources in Lsp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lsp environment.
This tool creates or modifies file content reversibly by reformatting code according to project standards (prettier, eslint, etc.). When apply=true, it writes changes to disk. This is a Write operation because the changes are reversible (formatting can be undone or re-run), not destructive.
From the tool's definition 'Format a file according to project style settings' and 'Set apply=true to write changes' — the tool modifies file content by applying formatting rules when apply=true is set.
Attacks that exploit this kind of access
Format a file according to project style settings (prettier, eslint, etc.). Use after making edits to ensure consistent formatting. Set apply=true to write changes. It is categorised as a Write tool in the Lsp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lsp MCP server in PolicyLayer and add a rule for lsp_format_document: 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 Lsp. Nothing to install.
lsp_format_document 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 lsp_format_document 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 lsp_format_document. 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.
lsp_format_document is provided by the Lsp MCP server (lsp-mcp-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 →