Call this to summarize and structurally inspect generated cn-font-split output files in an output directory. Inspect outputRoleDecision first: if outDir contains font-organization-manifest.json, it is organize_font_directory staging rather than generated split output, so inspect it with inspect_f...
AI agents call inspect_split_output to retrieve information from Mcp Font Split without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and analyzes existing output data without modifying, deleting, executing code, or making financial commitments. It is a diagnostic/inspection utility that queries file structures and metadata, which is characteristic of Read category operations with no side effects.
From the tool's definition Tool description states it is used to "summarize and structurally inspect generated cn-font-split output files" and "inspect outputStructureDecision, auditStatus, auditPassed, auditBlockingReasons, structureSummary" — purely informational operations.
Attacks that exploit this kind of access
Call this to summarize and structurally inspect generated cn-font-split output files in an output directory. Inspect outputRoleDecision first: if outDir contains font-organization-manifest.json, it is organize_font_directory staging rather than generated split output, so inspect it with inspect_font_inputs and split_font_batch safe-preview instead. Then inspect outputStructureDecision, auditStatus, auditPassed, auditBlockingReasons, structureSummary, maxFilesHit, and inspectionWarnings before treating an audit as complete; use includeFiles:false and includeFamilies:false for compact large-output summaries. It is categorised as a Read tool in the Mcp Font Split MCP Server, which means it retrieves data without modifying state.
Register the Mcp Font Split MCP server in PolicyLayer and add a rule for inspect_split_output: 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.
inspect_split_output is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the inspect_split_output 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 inspect_split_output. 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.
inspect_split_output 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 →