Call this when the user wants to split many local font files under a directory. dryRun defaults to false and can write output files; agents should set dryRun:true with includeResults:true to preview scan, dedupe, naming, skip decisions, sourceSafetyDecision, safetySummary, configurationTrace, bat...
AI agents use split_font_batch to create or update resources in Mcp Font Split — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Font Split environment.
split_font_batch creates and modifies files (WOFF2 fonts, CSS output) in the filesystem, making it a Write operation. While it can process many files in batch, source files are 'never moved or deleted' (explicitly stated), so it doesn't qualify as Destructive.
From the tool's definition Tool description states it 'can write output files' and 'writes Source Tree' (when outputRoot is inside inputDir). The parameters dryRun:false enables actual file writes, while dryRun:true is preview-only. The tool creates new WOFF2 font files and CSS output.
Attacks that exploit this kind of access
Call this when the user wants to split many local font files under a directory. dryRun defaults to false and can write output files; agents should set dryRun:true with includeResults:true to preview scan, dedupe, naming, skip decisions, sourceSafetyDecision, safetySummary, configurationTrace, batchPolicySummary, outputTreeInsideInputTree, batchDecision, recommendedNextActions[].suggestedArgsField, and batchWarnings before writing. Source font files are never moved or deleted, but writesSourceTree can be true when outputRoot is inside or equal to inputDir. If the directory shape is uncertain, call get_agent_guidance sections:[. It is categorised as a Write tool in the Mcp Font Split MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Font Split MCP server in PolicyLayer and add a rule for split_font_batch: 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 Font Split. Nothing to install.
split_font_batch 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 split_font_batch 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 split_font_batch. 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.
split_font_batch is provided by the Mcp Font Split MCP server (wenzhimo/mcp-font-split). 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 →