# Wells Software Consulting LLC

> Wells Software Consulting is a Chicago engineering practice that builds autonomous GTM and deal-desk systems, production MCP servers and agentic workflows, and the distributed, bare-metal and GPU infrastructure underneath them.

Office: 1 E Erie St, Suite 525-2098, Chicago, IL 60611. Phone: (312) 529-4614. Email: hello@wellsconsulting.com.

## Remote MCP server

Endpoint: https://wellsconsulting.com/mcp (MCP Streamable HTTP, JSON-RPC 2.0 over POST, no authentication).
Tools:
- get_consulting_services: practice areas, capabilities, contact details and the RentServers.com case study.
- estimate_project_scope: indicative duration and engagement shape for a described project.
- request_architecture_review: send a project summary and contact email to request a 30-minute architecture review.
Cursor: add {"mcpServers": {"wells": {"url": "https://wellsconsulting.com/mcp"}}} to ~/.cursor/mcp.json.
Claude Desktop: Settings, Connectors, Add custom connector, then paste the endpoint URL.

## Practice areas

- [Autonomous GTM & Deal-Desk Engineering](https://wellsconsulting.com/services/autonomous-gtm-engineering/): We replace manual prospecting and static brochure sites with signal-driven pipeline systems, interactive ROI and TCO calculators, and tokenized RFQ desks that qualify and price demand automatically.
  - [Revenue Platforms & Web Applications](https://wellsconsulting.com/services/web-application-development/): Server-rendered web platforms that carry revenue: buyer portals, quote and RFQ flows, calculators and the APIs behind them, built in Rust, TypeScript and Python.
- [Production MCP Servers & Agentic Workflows](https://wellsconsulting.com/services/mcp-agentic-systems/): We expose your product, catalog or pricing engine directly to AI agents (Claude Desktop, Cursor, OpenAI) through custom remote MCP servers, /llms.txt and high-concurrency Rust and Python APIs.
  - [Production AI Systems](https://wellsconsulting.com/services/ai-consulting/): Applied AI taken all the way to production: retrieval over your data, model integration behind a provider-agnostic interface, and the evaluation that proves it works.
  - [Agentic Workflows](https://wellsconsulting.com/services/agentic-workflows/): Multi-step automation that reads your systems, makes a decision and takes action, with approvals, audit trails and a stop button.
- [Distributed Systems & Bare-Metal/GPU Architecture](https://wellsconsulting.com/services/distributed-infrastructure/): End-to-end systems engineering, embedded and low-level software, and infrastructure cost optimization across cloud, bare metal and GPU.
  - [Embedded & Low-Level Systems](https://wellsconsulting.com/services/embedded-software-engineering/): Firmware and device software for constrained hardware, from board bring-up through field deployment, with updates that cannot brick a unit.
  - [Architecture Review & Fractional CTO](https://wellsconsulting.com/services/it-consulting/): Senior judgment when the decision is expensive: cloud versus bare metal, build versus buy, vendor selection and security posture.
  - [Managed Infrastructure Operations](https://wellsconsulting.com/services/it-services/): Ongoing operation of the infrastructure we build: provisioning, identity, backups, monitoring and on-call with a written response time.
  - [Mobile & Field Clients](https://wellsconsulting.com/services/mobile-app-development/): Native and cross-platform clients for the systems we build: field-service apps, device companions and operator consoles that work offline and pass store review.
  - [After-Hours Support](https://wellsconsulting.com/services/after-hours-support/): Emergency software support when production breaks overnight: outages, failed deploys, cloud, database, DNS and SSL. A principal engineer from 7 PM to 6 AM Central.

## Case study

- [Case study: RentServers.com: Autonomous GPU and bare-metal clearinghouse](https://wellsconsulting.com/case-studies/rentservers/): A GPU and bare-metal infrastructure marketplace engineered as an autonomous deal desk: Rust/Axum server-rendered quote ingestion, a 36-month TCO normalization engine, and automated multi-vendor inventory clearing. Result: Shipped from zero to a production clearinghouse in under 14 days, normalizing multi-vendor bare-metal and GPU quotes with server-rendered pages delivered in under 40 ms and native MCP agent discovery.

## Engage

- [Scope a project](https://wellsconsulting.com/scope/): two-path scoping form (A: autonomous deal desk or revenue pipeline; B: MCP server, AI agent or systems architecture). Written range within one business day.
- [Contact](https://wellsconsulting.com/contact/)

## Optional

- [About](https://wellsconsulting.com/about/)
- [Support](https://wellsconsulting.com/support/)