// MCP TOOL REFERENCE

RUBE TOOLS

11 tools from the Rube MCP Server, categorised by risk level.

View the Rube policy → Token cost: 10,766 tokens →

// ALL 11 RUBE TOOLS

READ 4 tools

Read RUBE_FIND_RECIPE Find recipes using natural language search. Use this tool when: - User refers to a recipe by partial name,... Read RUBE_GET_RECIPE_DETAILS Get the details of the existing recipe for a given recipe id. Read RUBE_GET_TOOL_SCHEMAS Retrieve input schemas for tools by slug. Returns complete parameter definitions required to execute each t... Read RUBE_SEARCH_TOOLS MCP Server Info: COMPOSIO MCP connects 500+ apps—Slack, GitHub, Notion, Google Workspace (Gmail, Sheets,...

WRITE 3 tools

Write RUBE_CREATE_UPDATE_RECIPE Convert executed workflow into a reusable notebook. Only use when workflow is complete or user explicitly r... Write RUBE_MANAGE_CONNECTIONS Create or manage connections to user's apps. Returns a branded authentication link that works for OAuth, A... Write RUBE_MANAGE_RECIPE_SCHEDULE Manage scheduled recurring runs for recipes. Each recipe can have one schedule that runs indefinitely. ...

DESTRUCTIVE 1 tools

Destructive RUBE_REMOTE_WORKBENCH Process **REMOTE FILES** or script BULK TOOL EXECUTIONS using Python code IN A REMOTE SANDBOX. If you ca...

EXECUTE 3 tools

Execute RUBE_EXECUTE_RECIPE Executes a Recipe Execute RUBE_MULTI_EXECUTE_TOOL Fast and parallel tool executor for tools and recipes discovered through RUBE_SEARCH_TOOLS. Use this too... Execute RUBE_REMOTE_BASH_TOOL Execute bash commands in a REMOTE sandbox for file operations, data processing, and system tasks. Essent...

// FAQ

How many tools does the Rube MCP server have? +

The Rube MCP server exposes 11 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Rube tools? +

Route the Rube server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Rube tools fall into? +

Rube tools are categorised as Read (4), Write (3), Destructive (1), Execute (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.