Call this first when an AI coding assistant needs to choose a safe font-splitting workflow. It returns workspace path rules, projectStatusNotice, toolSafetyQuickReference, nextToolDecisionSummary with workflowQuickStart and quickStartCallExamples, configurationRecipes, batchCustomizationQuickRefe...
AI agents call get_agent_guidance 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.
get_agent_guidance is a reference/lookup tool that retrieves configuration guidance, safety information, and workflow documentation. It performs no write operations, does not execute commands or scripts, does not delete data, and does not move money. The tool simply provides read-only information to help agents make decisions about font-splitting workflows.
From the tool's definition Tool returns guidance information: 'workspace path rules, projectStatusNotice, toolSafetyQuickReference, nextToolDecisionSummary' and various catalogs and references. These are all informational outputs with no side effects.
Attacks that exploit this kind of access
Call this first when an AI coding assistant needs to choose a safe font-splitting workflow. It returns workspace path rules, projectStatusNotice, toolSafetyQuickReference, nextToolDecisionSummary with workflowQuickStart and quickStartCallExamples, configurationRecipes, batchCustomizationQuickReference, directoryOrganizationQuickAnswer, batchPolicyGuide, fontIdentityBasisCatalog, outputStructureCatalog, unsupportedFileCategoryCatalog, directoryHandlingModeCatalog, directoryWorkflowDecisionMatrix, directoryWorkflowExamples, safeInvocationTemplates, localVerificationOutputGuide, errorResponseCatalog, warningCodeCatalog, toolResponseFieldCatalog, recommended tool order, defaults, response fields to inspect, and successCriteria to satisfy before advancing. Use detailLevel or sections for a compact or focused response. 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 get_agent_guidance: 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.
get_agent_guidance 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 get_agent_guidance 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 get_agent_guidance. 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.
get_agent_guidance 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 →