---
title: "Composio integration for LuumenAI"
url: "https://www.luumen.ai/integrations/composio/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Composio integration for LuumenAI

Reach hundreds of apps through one catalogue, with writes held for approval

## What LuumenAI can do with Composio

LuumenAI connects to Composio without a credential of its own and exposes 19 tools (11 read-only · 3 write · 5 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: none required
- Tools available: 19 tools (11 read-only · 3 write · 5 destructive)
- Plan: available on all plans
- Category: AI & automation

## About Composio with LuumenAI

Composio is a single doorway to hundreds of connected apps — Slack, GitHub, Notion, Google Workspace, and more. Luumen can browse the toolkit catalogue, read tool schemas, and check which accounts are already connected. When a run needs a new connection or a trigger turned on, that step is previewed and approved before it happens.

## Example tools

Read-only (11 in total):

- `COMPOSIO_CHECK_ACTIVE_CONNECTION` — Deprecated: use check active connections instead for bulk operations.
- `COMPOSIO_CHECK_ACTIVE_CONNECTIONS` — Check active connection status for multiple toolkits or specific connected account ids.
- `COMPOSIO_CREATE_PLAN` — This is a workflow builder that ensures the LLM produces a complete, step-by-step plan for any use case.
- `COMPOSIO_GET_REQUIRED_PARAMETERS` — Gets the required parameters for connecting to a toolkit via initiate connection.
- `COMPOSIO_GET_RESPONSE_SCHEMA` — Retrieves the response schema for a specified composio tool.
- `COMPOSIO_GET_TOOL_SCHEMAS` — Retrieve input schemas for tools by slug.
- `COMPOSIO_LIST_TOOLKITS` — List all the available toolkits on composio with filtering options.
- `COMPOSIO_LIST_TRIGGERS` — List available triggers and their configuration schemas.

Write and destructive (8 in total, approval required by default):

- `COMPOSIO_ENABLE_TRIGGER` — Enable a specific trigger for the authenticated user.
- `COMPOSIO_EXECUTE_TOOL` — Execute a tool using the composio api.
- `COMPOSIO_GET_DEPENDENCY_GRAPH` — Get the dependency graph for a given tool, showing related parent tools that might be useful.
- `COMPOSIO_INITIATE_CONNECTION` — Initiate a connection to a toolkit with comprehensive authentication support.
- `COMPOSIO_MANAGE_CONNECTIONS` — Create or manage connections to user's apps.
- `COMPOSIO_MULTI_EXECUTE_TOOL` — Fast and parallel tool executor for tools discovered through COMPOSIO_SEARCH_TOOLS.
- `COMPOSIO_REMOTE_BASH_TOOL` — Execute bash commands in a REMOTE sandbox for file operations, data processing, and system tasks.
- `COMPOSIO_REMOTE_WORKBENCH` — Process **REMOTE FILES** or script BULK TOOL EXECUTIONS using Python code IN A REMOTE SANDBOX.

## Frequently asked questions

### How does LuumenAI connect to Composio?

Composio needs no credential of its own, so there is nothing to authorize. Access is still granted per agent, skill, and team inside Luumen, and every call is logged.

### Can LuumenAI change things in Composio on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 5 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to Composio — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/composio/