You asked Claude Code to add a query for orders by customer status. It generated a .scan()
with a FilterExpression
. Your Orders table has 50M rows and three functions already hammering the same partition key. Claude Code had no idea — it read your TypeScript files, not your AWS account.
That's the problem. AI coding assistants are literate in your source code. They are blind to your infrastructure.
When Claude Code reads your codebase, it builds a model of your application: function names, variable patterns, the string "Orders"
passed to DynamoDB.DocumentClient
. It can follow call chains, infer intent, and generate syntactically correct code.
What it cannot do is describe your actual infrastructure:
listAllOrders()
already does a full scan and costs $40/daySessions
So when you ask it to add a new query, it generates something that looks correct. It might use .query()
instead of .scan()
. But it'll query on an attribute with no index — because it has no way to know which attributes are indexed. It'll write a FilterExpression
that reads every item before filtering — which is exactly a scan, just spelled differently.
The code compiles. Tests pass. The problem ships.
infrawise gives Claude Code deterministic knowledge of your infrastructure through the Model Context Protocol. Three commands get you there.
1. infrawise init
cd your-project
infrawise init
Runs once per project. Detects your AWS profile and region, asks which databases you use, and writes a single file: infrawise.yaml
. That's the only file it creates in your repository — one config, no framework, no SDK changes.
2. infrawise doctor
infrawise doctor
Before you trust any analysis, verify that infrawise can actually reach your infrastructure. Doctor checks every configured adapter — DynamoDB, PostgreSQL, Lambda, S3 — and reports what's reachable.
This step matters more than it sounds. If your AWS credentials are stale or your DB password rotated, infrawise analyze
will run against cached metadata from last week and give you confident-but-wrong context. Doctor catches this before you feed stale data to Claude Code.
✓ DynamoDB Connected (profile: default)
✓ PostgreSQL Connected
✗ Lambda credentials expired
Fix what's broken, then move on.
3. infrawise dev
infrawise dev
The command you run while you work. It runs a fresh analysis of your repository and infrastructure, then starts an MCP server that Claude Code queries during code generation.
If no analysis cache exists, it runs one automatically. If your infrastructure changes — you add a GSI, a new Lambda, a new table — run infrawise dev
again and the context updates.
Register it with Claude Code once:
claude mcp add --transport http infrawise http://localhost:3000/mcp
From that point, every time Claude Code generates infrastructure-touching code, it queries this server first.
Here's what infrawise analyze
surfaces on a real project:
Findings 3 total
1. HIGH Full table scan detected on DynamoDB table "Orders"
listAllOrders() scans without any filter — reads every item in the table.
→ Replace Scan with Query using a partition key or add a GSI.
2. MED PostgreSQL table "users" has no index on column "email"
Filtering on "email" causes sequential scans.
→ CREATE INDEX CONCURRENTLY idx_users_email ON users(email);
3. MED DynamoDB table "Sessions" accessed by 6 distinct code paths
High access concentration may create hot partition issues at scale.
→ Consider write sharding or DynamoDB DAX for read-heavy workloads.
These aren't generic warnings. They name the function (listAllOrders
), the table (Orders
), and the exact fix (CREATE INDEX CONCURRENTLY idx_users_email ON users(email)
). The GSI recommendation for DynamoDB includes the exact config — attribute name, key type, projection — not a suggestion to "consider adding an index."
When Claude Code queries the MCP server and gets this context:
.scan()
on Orders
— it knows the table has 50M rows and an existing high-severity finding.query()
— because it knows bothstatus
— because it knows that GSI already existsSessions
already has 6 access paths before adding a seventhYou're not getting a smarter model. You're giving the existing model the facts it was missing.
The gap between AI-generated code and production-safe code is mostly an information gap. Claude Code is capable of writing correct infrastructure queries — it just doesn't have your infrastructure. infrawise init
connects it. infrawise doctor
validates the connection. infrawise dev
keeps it current.
Three commands. One config file. No changes to your application code.
Key Takeaways
infrawise init
runs once and writes a single infrawise.yaml
to your projectinfrawise doctor
prevents you from trusting analysis built on stale or broken connectionsinfrawise dev
keeps infra context fresh automatically and serves it over MCP