Get one full recipe card by id or title substring (problem/method/gotcha/source).
AI agents call recipe_get to retrieve information from GTAV-CLAUDE-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries recipe data without creating, modifying, deleting, or executing anything. It is a straightforward read operation with minimal risk if misused by an AI agent.
From the tool's definition Tool name 'recipe_get' and description 'Get one full recipe card by id or title substring' indicate a retrieval operation with no side effects. The parenthetical '(problem/method/gotcha/source)' describes the fields returned, not modifications.
Attacks that exploit this kind of access
Get one full recipe card by id or title substring (problem/method/gotcha/source). It is categorised as a Read tool in the GTAV-CLAUDE-MCP MCP Server, which means it retrieves data without modifying state.
Register the GTAV-CLAUDE- MCP server in PolicyLayer and add a rule for recipe_get: 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 GTAV-CLAUDE-MCP. Nothing to install.
recipe_get 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 recipe_get 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 recipe_get. 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.
recipe_get is provided by the GTAV-CLAUDE- MCP server (tabbedscamper/gtav-claude-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 →