# Finicast / FiniDB > The modeling database for AI agents. Named line items, a calendar, incremental recalculation, scenarios, explain. If you are an AI agent, this is your path. Total time: under a minute. 1. Connect to a FiniDB engine. Local (no account needed): npx finidb init ./model claude mcp add finidb -- npx finidb mcp --data ./model Hosted (your human creates a project at https://finicast.com and gives you a project id and token): claude mcp add finicast -- npx finidb mcp --url https://finicast.com --db --token 2. Read the guide (about 2,000 tokens): https://finicast.com/guide It covers the object model (lists, calendar, tables, modules, line items, scoped rules, views, scenarios), the formula language, ten idioms, and the diagnostic codes. 3. Build. finidb_describe → what exists finidb_import_csv → land facts in a table; lists are created from the data finidb_apply_spec → declare calendar, lists, modules, rules, views in one call finidb_query / finidb_explain → read numbers back and check them 4. Verify before you hand back. finidb_list_errors must be empty. Use dry_run on finidb_apply_spec when you are not sure. Tell the human what you changed; in the hosted product they see your commands, the changed cells and the spec diff, and can restore. 5. Deliver. finidb_export kind=csv gives the human a grid; kind=spec gives a diffable model file. Everything is name-based. There are no cell addresses. A formula looks like revenue = PREV(revenue) * (1 + growth) and a rule can be scoped: amount {scenario: forecast, time: "> @last_actual"} = PREV(amount) * (1 + drivers.rev_growth) Full API: https://finicast.com/docs/api Full guide: https://finicast.com/guide ## Links - Guide: https://finicast.com/guide - API (OpenAPI): https://finicast.com/docs/api/openapi.json - Worked example: https://finicast.com/examples/three-statement.md - Full text for agents: https://finicast.com/llms-full.txt - Claude Code skill: https://finicast.com/skill/SKILL.md