Infrawise
MCP server that statically analyzes codebase, infra and schemas for AI assistants.
Tested on Linux
Use it
Linux x86_64
You need first
- Runtimes:
Node.js 22 or later - System packages:
python3
install infrawise globally via npm
npm install -g infrawise
Check that it works
infrawise --version; infrawise --helpThe output should contain “1.0.0”.
Add it to your agent
claude mcp add infrawise -- infrawise serve --stdio --config '<config>'JSON for Claude Desktop, Cursor and other clients
{
"mcpServers": {
"infrawise": {
"command": "infrawise",
"args": [
"serve",
"--stdio",
"--config",
"<config>"
]
}
}
}Replace <config> with your own path.
Add Infrawise as an MCP server in your AI assistant's settings, then ask the assistant for an infrastructure overview to start.
What it does
- Analyze your code and cloud infrastructureNot shown working
- Find infrastructure and query anti-patternsNot shown working
- Get GSI and index suggestionsNot shown working
- Find drift between IaC and deployed resourcesNot shown working
How far pickfit got
Linux x86_64
- Installs
- Connects
- 0 of 4 features work
- Works offline
Good for
- Detect full table scans on DynamoDB tables
- Suggest missing PostgreSQL indexes
- Inspect SQS queues for DLQ and encryption issues
- Check Terraform and CloudFormation drift versus deployed state
- List API Gateway routes and Lambda integrations
How pickfit tested it
Each run starts from a clean machine and follows the steps above. How pickfit verifies
Linux x86_64
An MCP client called one of its tools
- Replayed from scratch
- Works offline
- Checked on 31 Oct 2026
- Version 1.0.0
An MCP client handshake over stdio listed 22 tools, and a call to get_infra_overview returned a result.