Amazon Bedrock agent
Amazon Bedrock agent for Spatial9: 4 free, MIT licensed files that connect agents and data platforms to the Spatial9 spatial audio MCP server and A2A agent.
Spatial9 on AWS and Amazon Bedrock
File · What it does
strands_agent.py · Bedrock agent built with Strands Agents, Spatial9 tools through MCPClient
spatial9_lambda.py · Lambda with start, status and save actions, key from Secrets Manager, files to S3
state_machine.json · Step Functions Map: 3 renders at a time, poll every 45 seconds
Run it
- Create a key at https://spatial9.ai/connect, then store it:
aws secretsmanager create-secret --name spatial9/api-key --secret-string '{"api_key":"s9_..."}' - Deploy
spatial9_lambda.py(withspatial9_mcp.pyandrequests) as a function namedspatial9. Give it read access to the secret and write access to the bucket. - Create the state machine from
state_machine.jsonand start it with{"tracks": [{"track_id": "0042", "title": "Northern Lights", "source_url": "https://..."}]}.
Bedrock AgentCore and Bedrock Agents
- AgentCore Runtime can host the Strands agent. AgentCore Gateway can front Spatial9 as an MCP target so many agents share one governed connection, with AgentCore Identity holding the key.
- Classic Bedrock Agents can call the same Lambda as an action group.
- Service names and console steps change often. Check the current AWS docs before you deploy.