Infrawise
An MCP server that gives AI coding assistants deterministic knowledge of a project's actual AWS infrastructure and database schemas, instead of letting them guess from source code alone.
Infrawise statically analyzes a codebase, its cloud infrastructure, and its database schemas, then exposes that context to AI coding assistants such as Claude Code, Cursor, and GitHub Copilot through MCP. It covers services including DynamoDB, Lambda, SQS, SNS, S3, API Gateway, PostgreSQL, MySQL, MongoDB, and Kafka, along with infrastructure-as-code drift detection.
The stated problem is that an AI assistant reading only source files does not know which indexes already exist, how tables are partitioned, or which functions already query a given partition key, and so may suggest a full table scan, a duplicate index, or an unnecessarily expensive query. With Infrawise, the assistant instead has the exact table schemas, partition and sort keys, and which functions query which tables.
Running infrawise start --claude probes the environment, asks which AWS profile to use if there are several, scans AWS services, databases, and the codebase, and writes an MCP configuration file so the editor auto-connects on every later launch.