Infrawise

by Sidd27

307 downloads
Not rated
GitHub

About

Gives AI coding assistants deterministic infrastructure awareness. Statically analyzes your codebase, AWS services, and database schemas — exposes DynamoDB tables, indexes, query patterns, and service relationships via MCP so Claude Code knows your actual infrastructure instead o

Details

Author
Sidd27
Downloads
307
Categories
Database, Infrastructure

- Complete infrastructure snapshot with counts and high-severity findings
- Full infrastructure graph displaying all nodes, edges, and findings
- Function-level analysis including scans, missing indexes, and N+1 issues
- Exact GSI configuration suggestions for DynamoDB tables
- SQL index suggestions for PostgreSQL, MySQL, and MongoDB
- SQS queue details including DLQ status, encryption, and message counts
- Secrets Manager overview with rotation status (values never included)

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Infrawise
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install globally via npm (npm install -g infrawise), run infrawise init in your project directory, then add the server to Claude Code's MCP configuration in ~/.claude/settings.json with the command infrawise dev.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "infrawise": {
            "infrawise": {
                "command": "npx",
                "args": [
                    "-y",
                    "infrawise",
                    "dev",
                    "--config",
                    "infrawise.yaml"
                ]
            }
        }
    }
}

McpServers

{
    "infrawise": {
        "command": "npx",
        "args": [
            "-y",
            "infrawise",
            "dev",
            "--config",
            "infrawise.yaml"
        ]
    }
}

What it does

Infrawise gives AI coding assistants deterministic infrastructure awareness. Instead of guessing from source files, Claude Code can query your actual AWS tables, indexes, Lambda configs, SQS queues, and database schemas through MCP. All analysis is deterministic — AST parsing, schema introspection, and rule-based analyzers. No LLM involved in the analysis itself. ## Available tools | Tool | What it provides | |---|---| | get_infra_overview | Complete snapshot — all services, counts, and high-severity findings | | get_graph_summary | Full infrastructure graph — all nodes, edges, and findings | | analyze_function | Issues in a specific function — scans, missing indexes, N+1 | | suggest_gsi | Exact GSI config for a DynamoDB table + attribute | | postgres_index_suggestions | Exact CREATE INDEX SQL for your actual table | | suggest_mongo_index | Exact createIndex command for a MongoDB collection + field | | mysql_index_suggestions | Exact ALTER TABLE ADD INDEX SQL for your MySQL table | | get_queue_details | SQS queues — DLQ status, encryption, message counts | | get_topic_details | SNS topics — subscription counts and protocols | | get_secrets_overview | Secrets Manager — names and rotation status (values never included) | | get_parameter_overview | SSM Parameter Store — names, types, tiers (values never included) | | get_lambda_overview | Lambda functions — runtime, memory, timeout, env var key names | | get_log_errors | CloudWatch error patterns and counts (no raw log messages) | ## Setup 1. Install and initialize ``bash npm install -g infrawise cd your-project infrawise init 2. Add to Claude Code (~/.claude/settings.json): { "mcpServers": { "infrawise": { "command": "infrawise", "args": ["dev"] } } } ``

Security

- Read-only — never writes to AWS or your database - Local-first — nothing sent to external servers - No telemetry - Secret and parameter values are never included in any tool response
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.