Infrawise – Give Claude Code real infrastructure context via MCP

sidd-27041 pts0 comments

infrawise - npm

npm

Search<br>Sign UpSign In

infrawise<br>0.6.0 • Public • Published 4 days ago<br>Readme<br>Code Beta<br>23 Dependencies<br>0 Dependents<br>11 Versions<br>Infrawise

Understand your infrastructure, not just your code.

Infrawise gives AI coding assistants deterministic infrastructure awareness.

It statically analyzes your codebase, cloud infrastructure, and database schemas, then exposes that context through MCP so tools like Claude Code can understand your actual tables, indexes, query patterns, and service relationships instead of guessing from source files alone.

Why this exists

AI coding assistants can read your source files but have no deterministic knowledge of your infrastructure. They do not know which GSIs exist, how tables are partitioned, which functions already trigger scans, or where indexes are missing. So they guess.

Infrawise replaces guessing with infrastructure-aware context.

Without Infrawise , an AI assistant might:

Suggest a .scan() on your Orders table that has 50M rows

Recommend adding a GSI on status that you already have

Write a SELECT * when you need to keep query cost low

Not notice that 5 functions are already hammering the same partition key

With Infrawise , it knows:

Your exact table schemas, partition keys, sort keys, and GSIs

Which functions query which tables and how

Which patterns are already flagged as high severity

The exact CREATE INDEX SQL or GSI config for your tables — not generic advice

What Infrawise is not

Infrawise is not an AI agent framework, an infrastructure provisioning tool, an observability platform, or a cloud management dashboard.

It is a deterministic infrastructure intelligence layer for AI-assisted development.

Installation

npm install -g infrawise

or use without installing:

npx infrawise init

Quick start

1. Initialize in your repo

cd your-project<br>infrawise init

Detects your AWS profile and region, asks a few questions, writes infrawise.yaml. That's the only file it creates in your project.

2. Validate everything is connected

infrawise doctor

3. Run analysis

infrawise analyze

Or skip this step — infrawise dev auto-runs analysis if no cache exists.

Findings (3 total)

1. [HIGH] Full table scan detected on DynamoDB table "Orders"<br>listAllOrders() scans without any filter — reads every item in the table.<br>Recommendation: Replace Scan with Query using a partition key or add a GSI.

2. [MEDIUM] PostgreSQL table "users" has no index on column "email"<br>Filtering on "email" causes sequential scans.<br>Recommendation: CREATE INDEX CONCURRENTLY idx_users_email ON users(email);

3. [MEDIUM] DynamoDB table "Sessions" accessed by 6 distinct code paths<br>High access concentration may create hot partition issues at scale.

Using with AI coding assistants

Step 1: Start the MCP server

infrawise dev

✔ Config loaded infrawise.yaml<br>✔ Cached analysis loaded 42 nodes · 18 edges · 7 finding(s)<br>✔ Server running

┌────────────────────────────────────────────────────┐<br>│ MCP Server │<br>├────────────────────────────────────────────────────┤<br>│ POST http://localhost:3000/mcp │<br>│ GET http://localhost:3000/health │<br>├────────────────────────────────────────────────────┤<br>│ Tools (13 active) │<br>│ get_infra_overview · get_graph_summary │<br>│ ... │<br>└────────────────────────────────────────────────────┘

Watching for file changes... Press Ctrl+C to stop

Step 2: Add to your editor settings

Claude Code — edit .claude/settings.json in your repo (project-level) or ~/.claude/settings.json (global):

"mcpServers": {<br>"infrawise": {<br>"url": "http://localhost:3000/mcp"

To let Claude Code manage the server lifecycle automatically:

"mcpServers": {<br>"infrawise": {<br>"command": "infrawise",<br>"args": ["dev"]

Cursor and Windsurf — add http://localhost:3000/mcp as an MCP server in editor settings.

MCP tools

Tool<br>What it provides

get_infra_overview<br>Complete snapshot — all services, counts, and high-severity findings

get_graph_summary<br>Full infrastructure graph — all nodes, edges, and findings

analyze_function<br>Issues in a specific function — scans, missing indexes, N+1

suggest_gsi<br>Exact GSI config for a DynamoDB table + attribute

postgres_index_suggestions<br>Exact CREATE INDEX SQL for your actual table

suggest_mongo_index<br>Exact createIndex command for a MongoDB collection + field

mysql_index_suggestions<br>Exact ALTER TABLE ADD INDEX SQL for your MySQL table

get_queue_details<br>SQS queues — DLQ status, encryption, message counts

get_topic_details<br>SNS topics — subscription counts and protocols

get_secrets_overview<br>Secrets Manager — names and rotation status (values never included)

get_parameter_overview<br>SSM Parameter Store — names, types, tiers (values never included)

get_lambda_overview<br>Lambda functions — runtime, memory, timeout, env var key names

get_log_errors<br>CloudWatch error patterns and counts (no raw log messages)

CLI reference

Command<br>What it does

infrawise init<br>Detect AWS + repo, generate infrawise.yaml

infrawise auth<br>Select or switch AWS profile

infrawise...

infrawise table infrastructure code claude exact

Related Articles