Call this before large batch runs to scan supported font files, validate basic font metadata parsing, report identity keys, glyph counts, invalid font-like files, layout, recommendedBatchPreviewArgs, inputDirectoryDecision, and inputDirectoryDecision.directoryOrganizationSafety without writing ou...
AI agents call inspect_font_inputs 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.
inspect_font_inputs performs inspection, validation, and reporting of font file metadata without modifying or writing any output. It gathers information to inform subsequent batch operations but takes no actions that alter state. This is a classic Read operation with minimal blast radius—misuse would merely return incorrect metadata, not corrupt data or trigger unwanted changes.
From the tool's definition Tool description states it 'scan[s] supported font files, validate[s] basic font metadata parsing, report[s] identity keys, glyph counts, invalid font-like files, layout' and explicitly 'without writing output.' The prefix 'inspect_' and verbs 'scan,'…
Attacks that exploit this kind of access
Call this before large batch runs to scan supported font files, validate basic font metadata parsing, report identity keys, glyph counts, invalid font-like files, layout, recommendedBatchPreviewArgs, inputDirectoryDecision, and inputDirectoryDecision.directoryOrganizationSafety without writing output. inputDirectoryDecision gives a first-pass route for direct safe batch preview versus non-destructive organize_font_directory safe-preview. inputDirectoryDecision.directoryOrganizationSafety gives the shortest answer for whether organize_font_directory is available, whether it writes by default, and whether reviewed organization can change source files. recommendedBatchPreviewArgs preserves the current maxFiles scan cap for copyable follow-up previews. 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_font_inputs: 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_font_inputs 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_font_inputs 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_font_inputs. 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_font_inputs 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 →