Foundation MCP server

Foundation Skills

Open-source agent skills that do a feasibility consultant's job: size the market, benchmark competitors, build the financial study, tune the pricing, then write the business plan and the pitch deck. They run in your own AI agent (Claude, Codex, Gemini CLI, Cursor and others). They are built by the team behind Foundation.

▶ Foundation in 48 seconds: a sample café project from its costs to its business plan, and an AI assistant testing it.

Why this exists

Ask a general AI assistant whether your business idea works and it will write you something that sounds like a feasibility study. The problems are underneath:

break-even figures in an AI-written plan are often wrong, and nothing on the page tells you which ones.

• The math is guessed. Language models are not calculators. NPV, IRR, payback and

will ask, and "the AI said so" is not an answer.

• The assumptions are invisible. Where did "£38,000 for the fit-out" come from? A lender

the market chapter uses a different number from the pitch deck.

• The parts don't agree. The team section says five staff, the payroll line pays four, and

A professional consultant avoids all three. They put a source behind every input, run the numbers through a real financial model, and keep one version of the truth that every document draws from. These skills teach an AI agent to work the same way.

How it works

The skills split the job the way it should be split:

and competitors, choosing a sensible structure, tagging where every number came from, and writing.

• The agent does the analyst's work: interviewing the founder, researching costs, prices

feasibility-study web app with a tested calculation engine. It computes investment, operating costs, revenue ramps, profit, cash flow, NPV, IRR, payback, break-even and SaaS metrics from the inputs. When your agent is connected to Foundation, every financial figure in the output comes from that engine. The agent never computes one itself.

• A deterministic engine does the math: Foundation is a

The skills also work without a Foundation account. The agent still does the research and structures every input with its source, and never invents financial results. It then hands you a foundation-project.json file. Import that file into Foundation (Projects → Import) to get the computed study.

The skills

Shortened. The full README is on GitHub.