Amazon SQS
Connect AI agents and workflows to Amazon SQS: send, read and delete queue messages, and start work when new messages arrive.
Book a demoAmazon SQS for AI agents and workflows.
engini lets your workflows and agents work with Amazon SQS queues: send messages, read them and delete them once handled, and start a workflow when new messages arrive. Events from your own applications reach your ERP, CRM and databases through a queue, with every step on record. Connect from Claude, ChatGPT or Cursor over MCP, from your code, or build in Workflow Studio.
Cursor, your code
audit log
in engini
What your agent can do in Amazon SQS. Every tool is one you allow or leave out.
The Amazon SQS tools in engini, grouped by what they change. Read tools are safe to hand out widely. Write and delete tools go only to the agents that need them.
Read
Read messages from a queue.
Write
Send a message to a queue.
Delete
Remove a message once it is handled.
Triggers
New messages in the queue you choose.
A trigger starts a workflow, and a workflow can include an AI agent step. In Code, a trigger delivers the event to your own endpoint.
Connect your AI agent to Amazon SQS. Four ways in, one set of permissions.
Claude, ChatGPT, Cursor
Create an MCP server in engini with your Amazon SQS connection and only the tools you choose. Add its address to your client and sign in through engini. There is no key to copy.
MCP client setup →Python and TypeScript
Hand your agent a toolset of Amazon SQS tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.
SDK guide →For coding agents
The engini CLI connects Amazon SQS and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.
CLI guide →Any language
Every Amazon SQS tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.
API reference →.cursor/mcp.json. Claude Code: claude mcp add.// .cursor/mcp.json: Cursor, connected to Amazon SQS through engini
{
"mcpServers": {
"engini-amazon-sqs": {
"url": "<your engini MCP server address>"
}
}
}
Create the MCP server in engini with your Amazon SQS connection and the tools this agent may use, then paste its address. The client signs in through engini on first use. Claude, VS Code and other clients take the same address: see the MCP client setup guide.
Each request runs through the Amazon SQS tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.
What teams build on Amazon SQS. Agents and workflows, across systems.
App events into the ERP
Your application drops order events on a queue; a workflow reads them and creates the sales orders in NetSuite or SAP.
Failures, handled
Messages in a dead-letter queue start a workflow that opens a ticket with the details.
Changes into the warehouse
Change events on a queue are written to Snowflake as they arrive.
Work handed back to your apps
A workflow finishes in the ERP and sends a message to a queue your application reads.
Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between Amazon SQS and another system engini connects is available.
You decide what each agent may do in Amazon SQS. engini enforces it on every call.
Only the tools you allow
A toolset lists the Amazon SQS tools an agent may call and the connection each one uses. Give one agent read tools only and another the write it needs. engini refuses any call outside the toolset.
Scoped when you set them up
An MCP server exposes only the connections and tools chosen when it is created, and engini shows who uses each server.
Whose permissions apply
Connect a person's own Amazon SQS account and engini acts as that person, with their Amazon SQS permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.
Kept out of prompts
Your agent never needs your credentials: engini stores them and adds them when it runs each call, so keys stay out of prompts and tool inputs.
Every call on record
Every call lands in History and the audit log, which you can export or stream to your SIEM.
Test before production
Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.
Connect Amazon SQS in three steps. Then decide what each agent may do.
Sign in to Amazon SQS
Create an AWS access key with access to your queues, then add an Amazon SQS connection with the key, the secret and the Region.
Choose the tools
Add the connection to an MCP server or a toolset with only the tools each agent needs.
Build or ask
Use the connection as a step in a workflow, or ask your agent to work in Amazon SQS from Claude, ChatGPT, Cursor or your own code.
Amazon SQS and engini. Straight answers.
Can an AI agent write to Amazon SQS, or only read?
Both. engini has tools to send and delete queue messages. Whether a given agent may use them is up to you: give it a toolset or an MCP server with read tools only, and it cannot call the rest.
Does the agent act as me in Amazon SQS?
It acts as the AWS identity behind the access key, with that identity's permissions on your queues. Every run is recorded under the person who started it.
Can a change in Amazon SQS start work?
Yes. A scheduled trigger checks for new messages in the queue you choose. The workflow can include an AI agent step.