Get user budget categories.
AI agents call get_categories to retrieve information from Corpus MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves existing budget category information belonging to the user. It does not create, modify, delete, or execute operations. The blast radius of misuse is minimal—an AI agent could at worst view which budget categories exist, with no capability to alter financial state or trigger transactions. Classified as Read with low severity.
From the tool's definition Tool name 'get_categories' and description 'Get user budget categories' indicate a retrieval operation with no side effects. The verb 'get' and the read-only nature of querying budget category metadata confirm this is a data retrieval action.
Attacks that exploit this kind of access
Get user budget categories. It is categorised as a Read tool in the Corpus MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Corpus MCP Server MCP server in PolicyLayer and add a rule for get_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 Corpus MCP Server. Nothing to install.
get_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_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_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_categories is provided by the Corpus MCP Server MCP server (mathankarthik18/corpus-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 →