Find recipes using natural language search. Use this tool when: - User refers to a recipe by partial name, description, or keywords (e.g., "run my GitHub PR recipe", "the slack notification one") - User wants to find a recipe but doesn't know the exact name or ID - You need to find a recipe_id be...
Risk signalsAccepts freeform code/query input (query)
Part of the Rube server.
Free to start. No card required.
AI agents call RUBE_FIND_RECIPE to retrieve information from Rube without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though RUBE_FIND_RECIPE only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"RUBE_FIND_RECIPE": {}
}
}See the full Rube policy for all 11 tools.
These attack patterns abuse exactly the kind of access RUBE_FIND_RECIPE gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Find recipes using natural language search. Use this tool when: - User refers to a recipe by partial name, description, or keywords (e.g., "run my GitHub PR recipe", "the slack notification one") - User wants to find a recipe but doesn't know the exact name or ID - You need to find a recipe_id before executing it with RUBE_EXECUTE_RECIPE The tool uses semantic matching to find the most relevant recipes based on the user's query. Input: - query (required): Natural language search query (e.g., "GitHub PRs to Slack", "daily email summary") - limit (optional, default: 5): Maximum number of recipes to return (1-20) - include_details (optional, default: false): Include full details like description, toolkits, tools, and default params Output: - successful: Whether the search completed successfully - recipes: Array of matching recipes sorted by relevance score, each containing: - recipe_id: Use this with RUBE_EXECUTE_RECIPE - name: Recipe name - description: What the recipe does - relevance_score: 0-100 match score - match_reason: Why this recipe matched - toolkits: Apps used (e.g., github, slack) - recipe_url: Link to view/edit - default_params: Default input parameters - total_recipes_searched: How many recipes were searched - query_interpretation: How the search query was understood - error: Error message if search failed Example flow: User: "Run my recipe that sends GitHub PRs to Slack" 1. Call RUBE_FIND_RECIPE with query: "GitHub PRs to Slack" 2. Get matching recipe with recipe_id 3. Call RUBE_EXECUTE_RECIPE with that recipe_id. It is categorised as a Read tool in the Rube MCP Server, which means it retrieves data without modifying state.
Register the Rube MCP server in PolicyLayer and add a rule for RUBE_FIND_RECIPE: 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 Rube. Nothing to install.
RUBE_FIND_RECIPE 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 RUBE_FIND_RECIPE 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 RUBE_FIND_RECIPE. 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.
RUBE_FIND_RECIPE is provided by the Rube MCP server (Composio/Rube). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Rube tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.