Get list of available BPA rule categories.
AI agents call get_bpa_categories to retrieve information from Semantic Model MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple retrieval of metadata (list of rule categories) from the Best Practice Analyzer. It does not modify, delete, execute code, or commit financial operations. It is a Read operation with minimal blast radius if misused, as an AI agent cannot cause harm by listing available categories.
From the tool's definition Tool name 'get_bpa_categories' and description indicate it retrieves or lists available BPA (Best Practice Analyzer) rule categories—a query operation with no side effects.
Attacks that exploit this kind of access
Get list of available BPA rule categories. It is categorised as a Read tool in the Semantic Model MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Semantic Model MCP Server MCP server in PolicyLayer and add a rule for get_bpa_categories: 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 Semantic Model MCP Server. Nothing to install.
get_bpa_categories 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_bpa_categories 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_bpa_categories. 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_bpa_categories is provided by the Semantic Model MCP Server MCP server (nahtheking/semantic-model-mcp). 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 →