< Back to all integrations

AWS Bedrock

AI & Machine Learning

Use AWS Bedrock models in engini with your Bedrock key and Region: chat, invoke, images, embeddings, guardrails, and as the model behind an AI agent step.

Book a demo
[ AWS Bedrock + engini ]

AWS Bedrock for AI agents and workflows.

engini calls the foundation models you use on AWS Bedrock, in the Region you choose, with your own Bedrock key: chat completions, direct model invocation, image generation, text embeddings, token counts and guardrails. Bedrock can also be the model behind an AI agent step in a workflow, so the agent reasons with a model in your AWS account while engini governs what it may do in your systems.

MCPPython and TypeScript SDKCLIREST APIWorkflow Studio
Read the AWS Bedrock guide →
Sign-inA Bedrock API key and the AWS Region you use
ModelsThe foundation models and inference profiles your key may use in that Region
Agent stepBedrock as the model of an AI agent step
[ 01 / What agents can do ]

What a workflow can do with AWS Bedrock. Every tool is one you allow or leave out.

The AWS Bedrock tools in engini, for calling your models from a workflow step or from your code.

Model

Create Chat Completion, Invoke Model

Get a reply from a model.

Model
Generate Image, Generate Text Embedding

Images and embeddings.

Model
Apply Guardrail

Check content against a Bedrock guardrail.

Model
Count Tokens

Count tokens before you send.

Model

Catalog

Get Foundation Models, Get Foundation Model, Get Inference Profiles

See what your key can use in the Region.

Read

Any endpoint

Send API Request

Call any Bedrock endpoint, with the key added for you.

Any call

Triggers

There are no Bedrock triggers. A model step runs inside a workflow started by any other trigger.

[ 02 / Connect your agent ]

Connect your AI agent to AWS Bedrock. Four ways in, one set of permissions.

MCP

Claude, ChatGPT, Cursor

Create an MCP server in engini with your AWS Bedrock 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 →
SDK

Python and TypeScript

Hand your agent a toolset of AWS Bedrock tools. The SDK gives OpenAI and Anthropic models the tools in the format they expect and runs the ones they pick.

SDK guide →
CLI

For coding agents

The engini CLI connects AWS Bedrock and runs its tools from a terminal, with machine-readable output, so an AI coding agent can drive it without getting stuck.

CLI guide →
REST API

Any language

Every AWS Bedrock tool is an endpoint. Call it with exact inputs from a scheduled job or a sync, with no model in the loop.

API reference →
MCP in four steps
In engini, connect AWS Bedrock and create an MCP server with that connection and the tools this agent may use.
Claude: Settings, Connectors, Add custom connector, then paste the server address.
Cursor: add the address to .cursor/mcp.json. Claude Code: claude mcp add.
Sign in through engini when the client asks. The agent sees only the tools you chose.
Cursor, connected to AWS Bedrock through engini
// .cursor/mcp.json: Cursor, connected to AWS Bedrock through engini
{
"mcpServers": {
"engini-aws-bedrock": {
"url": "<your engini MCP server address>"
}
}
}

Create the MCP server in engini with your AWS Bedrock 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.

Try asking your agent
“Summarize this contract with the model we use on Bedrock.”
“Extract the line items from this invoice.”
“Check this reply against our guardrail before it goes out.”
“Which models can we use in us-east-1?”
“Embed these support articles for search.”
“Classify today's purchase requests by category.”

Each request runs through the AWS Bedrock tools in the agent's toolset or MCP server. If a tool is not allowed, the agent cannot call it.

[ 03 / What teams build ]

What teams build on AWS Bedrock. Agents and workflows, across systems.

Finance

Documents read inside your AWS account

Invoices and contracts are read by your Bedrock model, and the workflow writes the result to the ERP.

AWS BedrockNetSuite
Operations

An agent step on your own model

An AI agent step uses Bedrock as its model and works through the tools you give it in SAP or Salesforce.

AWS BedrockSAP S/4HANASalesforce
Support

Replies checked by a guardrail

Drafted replies pass a Bedrock guardrail before they reach Zendesk.

AWS BedrockZendesk
Search

Embeddings for your documents

Policy documents are embedded for search by your own agents.

AWS Bedrock

Every integration runs both ways, so any of these flows can also run in reverse. These are examples, not the limit: any flow between AWS Bedrock and another system engini connects is available.

[ 04 / Agent Policy ]

You decide what each agent may do in AWS Bedrock. engini enforces it on every call.

Toolsets

Only the tools you allow

A toolset lists the AWS Bedrock 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.

MCP servers

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.

Identity

Whose permissions apply

Connect a person's own AWS Bedrock account and engini acts as that person, with their AWS Bedrock permissions. Use a shared integration account and it acts as that account. Every run is recorded under the user who started it.

Credentials

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.

Audit

Every call on record

Every call lands in History and the audit log, which you can export or stream to your SIEM.

Environments

Test before production

Workspaces keep teams apart, and development, staging and production environments keep a test agent away from live data.

SOC 2 Type IIISO 27001GDPRSecurity at engini →
[ 05 / Set up ]

Connect AWS Bedrock in three steps. Then decide what each agent may do.

Step 01

Sign in to AWS Bedrock

Create a Bedrock API key in AWS that may use the models you need, then add an AWS Bedrock connection with the key and your Region.

Step 02

Choose the tools

Add the connection to an MCP server or a toolset with only the tools each agent needs.

Step 03

Build or ask

Use the connection as a step in a workflow, or ask your agent to work in AWS Bedrock from Claude, ChatGPT, Cursor or your own code.

Full AWS Bedrock setup guide →
[ 06 / Questions ]

AWS Bedrock and engini. Straight answers.

Can an AI agent write to AWS Bedrock, or only read?

Both. a Bedrock step returns text, images, embeddings or a guardrail result; what it can change in your systems depends on the workflow's steps and the tools you give the agent. 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.

Whose AWS account is used?

Yours. The connection holds your AWS Bedrock API key, engini adds it to each call, and usage is billed by AWS to your account.

Can the model change data in my systems?

Only through the tools you give it. A model step in a workflow returns text or data; what is written to your ERP or CRM is decided by the workflow's steps or by the toolset of the agent, and every call is recorded.

Does the agent act as me in AWS Bedrock?

Model calls use your Bedrock key, in your Region. Every run is recorded under the person who started it.

What if the tool I need is not listed?

Use Send API Request to call any AWS Bedrock API endpoint through the same connection, and give it only to the agents that need it.