Analyzes AWS infrastructure, code, and database schemas, then exposes findings and recommendations through MCP.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Infrawise.
get_infra_overviewComplete snapshot — services, counts, high-severity findings, `configured` flag (data age and per-source status ride the `dataHealth` block on every response)
get_graph_summaryFull infrastructure graph — all nodes, edges, and findings
get_table_schemaColumn-level schema for named tables/collections — types, PKs, FKs, indexes, DynamoDB keys/billing mode, cost signal (no row data)
analyze_functionIssues in a specific function — scans, missing indexes, N+1, trigger event shapes, missing IAM permissions; returns every same-named file as a separate match, or bind to one with the optional `file` input; names refused Lambda links and why (`unresolvedLambdas`)
suggest_gsiExact GSI config for a DynamoDB table + attribute — names the existing index instead when one already covers it
postgres_index_suggestionsExact `CREATE INDEX` SQL for your actual table
Sidd27/infrawise MCP server analyzes a codebase, AWS resources, and supported database schemas so an MCP client can query infrastructure facts instead of inferring them from source files. The analysis covers service relationships, Lambda usage, database access patterns, infrastructure findings, and selected configuration details.
Its responses can identify high-severity findings, data age, and per-source status through the dataHealth information. Database inspection is schema-level: table and collection names, columns, keys, foreign keys, indexes, and selected cost signals are available, but row data is not returned. Secrets Manager and SSM results expose names and metadata without secret or parameter values.
Run the command from the project directory. On first use, the CLI probes the environment and creates infrawise.yaml; when multiple AWS profiles are available, it asks which profile to use. It then scans AWS services, databases, and source code, writes an editor MCP configuration file, and connects the client to infrawise serve --stdio.
Analysis is cached for 24 hours. When the cache is stale, the stdio process refreshes it at session start. Changes to files are detected during a session and update the code graph automatically. An alternative HTTP transport is available at http://localhost:3000/mcp when the server is started with infrawise serve.
Node.js 22 or later is required. Install the npm package globally with npm install -g infrawise, or run it without a global installation using npx infrawise start --claude. The start command supports Claude Code, Cursor, and VS Code flags, and can also write a generic .mcp.json without opening an editor.
Claude Code uses .mcp.json, Cursor uses .cursor/mcp.json, and VS Code uses .vscode/mcp.json. These files are merged with existing MCP server entries. For a manually configured client, point the MCP command at infrawise serve --stdio --config /path/to/infrawise.yaml, replacing the path with the project’s actual configuration file.
Sidd27/infrawise MCP server exposes tools for infrastructure summaries and graph inspection, including service counts, findings, nodes, and edges. Function analysis can report scans, missing indexes, N+1 patterns, trigger event shapes, missing IAM permissions, duplicate function-name matches, and Lambda links that could not be resolved.
AWS-specific tools cover SQS queues, API Gateway routes, SNS topics, Secrets Manager, SSM Parameter Store, Lambda functions, EventBridge rules, S3 buckets, CloudWatch error patterns, Cognito pools, Kinesis streams, MSK clusters, ElastiCache, and CloudFront distributions. Other tools return table schemas or index recommendations for DynamoDB, PostgreSQL, MongoDB, and MySQL. Recommendations include concrete GSI configurations, CREATE INDEX statements, createIndex commands, or MySQL ALTER TABLE statements.
Infrawise is an analysis and context layer, not an infrastructure provisioning tool, AI agent framework, observability platform, or cloud management dashboard. Its outputs are based on scanned code, infrastructure, and schemas, so stale caches and unresolved Lambda links should be considered when interpreting results. Secret values, parameter values, database rows, and cache data are not read or included in the described outputs.
Factual signals from GitHub, npm, and our automated checks — not a rating.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/sidd27-infrawise)<a href="https://allmcps.com/mcp/sidd27-infrawise"><img src="https://allmcps.com/api/badge/sidd27-infrawise?style=directory" alt="Infrawise on AllMCPs" /></a>