Integration

Amazon Bedrock integration

Amazon Bedrock runtime and control plane: invoke any foundation model hosted on Bedrock, hold multi-turn conversations through the unified Converse API, generate embeddings, run guardrail checks, query a knowledge base with retrieval-augmented generation, and list the models and inference profiles available in the region. Authentication is AWS SigV4 with the region and the signing service name carried by the credential; the service name is always bedrock, including on the bedrock-runtime and bedrock-agent-runtime hosts.

Connect Amazon Bedrock How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Amazon Bedrock.Built from the 8 Amazon Bedrock tools below, on the connection you add once.

Common Amazon Bedrock use cases

discovering the exact model ids a region serves
using a vendor feature Converse does not expose
resolving the id a recent model must be called with
feeding retrieved context into a model of your choice
a support assistant grounded in internal documentation
screening user input before it reaches an expensive model
checking whether a model supports streaming before wiring it
running an LLM inside an AWS account for data-residency reasons
spreading load across regions
showing sources alongside an answer

What you can do with Amazon Bedrock

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Model, 3 operations

get_foundation_modelGet foundation modelGETRetrieves the details of one Bedrock foundation model.
invoke_modelInvoke modelPOSTInvokes a Bedrock model with its native vendor-specific request body.
list_foundation_modelsList foundation modelsGETLists the Bedrock foundation models available in the region.

Knowledge base, 2 operations

retrieve_and_generateRetrieve and generatePOSTAnswers a question from a Bedrock knowledge base with citations.
retrieve_from_knowledge_baseRetrieve from knowledge basePOSTRetrieves matching passages from a Bedrock knowledge base without generating an answer.

Conversation, 1 operation

converseConversePOSTRuns a conversation against any Bedrock model through the unified Converse API.

Guardrail, 1 operation

apply_guardrailApply guardrailPOSTScreens text against a Bedrock guardrail without invoking a model.

Inference profile, 1 operation

list_inference_profilesList inference profilesGETLists Bedrock inference profiles, including cross-region routing profiles.

Use Amazon Bedrock from Claude Code, Cursor or Codex

Connect Amazon Bedrock in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Amazon Bedrock operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Amazon Bedrock

Create your workspace
Sign up free. Nothing to install.
Connect Amazon Bedrock once
Add your Amazon Bedrock connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Amazon Bedrock integration FAQ

What can you do with the Amazon Bedrock integration?

LiveContext exposes 8 operations on Amazon Bedrock, covering model, knowledge base, conversation and guardrail. Common uses include discovering the exact model ids a region serves, using a vendor feature Converse does not expose and resolving the id a recent model must be called with.