$ ~/registry/skill/composiohq-composio-skills-langbase-automation

SKILL

langbase-automation

Name: langbase-automation
Author: Composio

Automate Langbase workflows through Rube MCP using current tool schemas.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

This skill is essentially an open-source prompt template with strong public provenance and high community adoption, so overall risk is relatively low. However, its real functionality depends on external Rube MCP and a Langbase connection, which introduces third-party network calls and account-authorization considerations.

CredentialsCaution

The material says the skill itself needs no keys or environment variables, but the README explicitly requires creating a Langbase connection through `RUBE_MANAGE_CONNECTIONS` and completing an auth link, indicating reliance on third-party managed account authorization or tokens. There is no clear sign of credential theft, but normal authorization misuse exposure exists.

Network egressCaution

The README requires adding `https://rube.app/mcp` as an MCP server and using Composio/Rube to search tools, manage connections, and execute operations. This means task instructions, arguments, and some business data will be sent to an external service. The endpoint is explicitly declared in the documentation, so this is expected network egress rather than hidden exfiltration.

Code executionLow risk

Based on the objective checks, this is a `prompt-only` skill. The material does not show local dependency installation, process spawning, or direct system-command execution; it mainly instructs how to call remote MCP tools rather than run local code.

Data accessCaution

The skill itself does not declare local file read/write access, but it can operate on resources in the connected Langbase account via Rube MCP, potentially accessing or modifying account data. This is consistent with the stated functionality, but it should be used with least-privilege access.

Supply chainCaution

Positive signals include being open-source on GitHub, auditable, and hosted in a repository with high community adoption (64.7k stars). However, this entry is only a skill description, while actual execution depends on externally hosted Rube/Composio services; the license is undeclared and maintenance status is unknown, so the supply-chain posture is best rated as caution rather than high risk.

Recommendations

Only connect `https://rube.app/mcp` in a trusted environment, and confirm your organization permits data processing via Rube/Composio.
Use a least-privilege account or test workspace when connecting Langbase, and avoid unnecessary write access.
Review the actual tool schemas returned by `RUBE_SEARCH_TOOLS` before execution to ensure actions stay within the intended scope.
Test in an isolated project first, and log the parameters and resulting changes sent through MCP.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "langbase-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/langbase-automation/SKILL.md
2. Save it as ~/.claude/skills/langbase-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Langbase Automation via Rube MCP

Automate Langbase operations through Composio's Langbase toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/langbase

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Langbase connection via RUBE_MANAGE_CONNECTIONS with toolkit langbase
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit langbase
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Langbase operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Langbase task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["langbase"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with Langbase-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `langbase`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`

Powered by Composio

Automate Landbot bot tasks and workflows through Rube MCP tool calls

ComposioGet→

$ loading_