Tech »  Topic »  Streamline AI agent tool interactions: Connect API Gateway to AgentCore Gateway with MCP

Streamline AI agent tool interactions: Connect API Gateway to AgentCore Gateway with MCP


AgentCore Gateway now supports API GatewayAs organizations explore the possibilities of agentic applications, they continue to navigate challenges of using enterprise data as context in invocation requests to large language models (LLMs) in a manner that is secure and aligned with enterprise policies. To help standardize and secure those interactions, many organizations are using the Model Context Protocol (MCP) specification, which defines how agentic applications can securely connect to data sources and tools.

While MCP has been advantageous for net new use cases, organizations also navigate challenges with bringing their existing API estate into the agentic era. MCP can certainly wrap existing APIs, but it requires additional work, translating requests from MCP to RESTful APIs, making sure security is maintained through the entire request flow, and applying the standard observability required for production deployments.

Amazon Bedrock AgentCore Gateway now supports Amazon API Gateway as a target, translating MCP requests to ...


Copyright of this story solely belongs to aws.amazon.com - machine-learning . To see the full text click HERE