fincraftly

AI employees that run your business and build your software, on every leading AI model, matched to each task.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Fincraftly Get Org Context: Get a compact, up-to-date summary of the AI Workforce: its departments, managers, employees, their statuses and emotions, plus recent activity. Call this before reasoning a
  • Fincraftly Get State: Get the AI Workforce structure and live stats: every department with its manager and AI employees (id, name, job title, role, agents), plus headcount and how many tasks are activ
  • Fincraftly List Tasks: List recent tasks in the AI Workforce with their statuses.

What data it sees

Do you need an account

No: the server works without sign-in

AI employees that run your business and build your software, on every leading AI model, matched to each task.

How to connect

How to connect fincraftly to Claude

The server address to paste into Claude settings:

https://fincraftly--jaysoni221717.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect fincraftly to ChatGPT

The server address to paste into ChatGPT settings:

https://fincraftly--jaysoni221717.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect fincraftly to Cursor

The server address to paste into Cursor settings:

https://fincraftly--jaysoni221717.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (30)

Raw names from tools/list. Only developers need these.

fincraftly_get_org_contextGet a compact, up-to-date summary of the AI Workforce: its departments, managers, employees, their statuses and emotions, plus recent activity. Call this before reasoning about the workforce.
fincraftly_get_stateGet the AI Workforce structure and live stats: every department with its manager and AI employees (id, name, job title, role, agents), plus headcount and how many tasks are active or completed.
fincraftly_list_tasksList recent tasks in the AI Workforce with their statuses.
fincraftly_list_outputsList the artifacts presented on a department's output canvas (titles, kinds, summaries).
fincraftly_create_departmentCreate a new department in the AI Workforce. It is always given a manager (auto-named unless you pass managerName), and the team posts its opening/welcome message in the department chat.
fincraftly_design_departmentDesign a department from a short brief: add a manager (only if one is missing) and new AI employees with their behaviour prompts. ADD-ONLY — never edits or removes existing people. Returns what was added.
fincraftly_assign_managerAssign a manager to a department so it can plan and review work.
fincraftly_add_employeeAdd an AI EMPLOYEE (a worker) to a department. An employee is NOT an agent: employees do the work and can be given agents (capabilities). Pass `agents` to choose those capabilities explicitly — you can only give agents you may use yourself; agents the role plainly requires are added on top, and the result reports both. To create an agent, use fincraftly_create_agent.
fincraftly_route_taskHand a unit of work to the AI Workforce. Optionally target a specific department by id; otherwise it lands in the org inbox for routing.
fincraftly_present_outputPresent a finished artifact on a department's output canvas so the user can view it — a document, code, data table, or summary the workforce produced. Use this whenever you generate something the user should be able to open and read.
fincraftly_create_agentCreate an AGENT in the Agents tab (Agent Studio) — a reusable capability with its own job description and optional tools that AI employees can be given. This is NOT an AI employee: employees are workers in a department; agents are the abilities they wield. Use fincraftly_add_employee for a worker.
fincraftly_integrations_contextGet a compact summary of the external capabilities this organization has connected: its MCP servers and its saved custom APIs (with their callable operations). Call this before deciding which MCP/API to use.
fincraftly_list_mcpsList the MCP servers this organization has connected (id, name, category, status). Use the id with the MCP tool functions.
fincraftly_list_mcp_toolsList the tools a connected MCP server exposes, so you know what you can call on it.
fincraftly_call_mcp_toolCall a tool on a connected MCP server (credentials are injected automatically). Returns the tool result.
fincraftly_list_apisList the custom APIs this organization has saved, with each API's callable operations (name, method, path template, description). URLs are shown as a hostname and a path template — the full address and its stored credentials are supplied by the platform when you call an operation with fincraftly_call_api.
fincraftly_call_apiCall a saved custom API with the stored credentials injected automatically. Either name a saved operation, or provide method+path for an ad-hoc request. Returns { ok, status, data }.
fincraftly_list_dashboardsList the dashboards in this workspace (id, name, description, card count). To read or change the cards ON a dashboard, use fincraftly_query / fincraftly_mutate with the "dashboards.cards.*" actions.
fincraftly_create_dashboardCreate a new EMPTY dashboard and return its id. A dashboard is only useful once it has cards on it: follow this with fincraftly_mutate action "dashboards.cards.create", and read the legal sources and fields first with fincraftly_query action "dashboards.sources.list".
fincraftly_list_contactsList the most recent contacts in the workspace CRM. For filtering, searching, paging or the other CRM record types (companies, customers, deals, products, expenses), use fincraftly_query.
fincraftly_create_contactQuickly save a contact with the common fields. The CRM contact record supports far more than this (status, priority, tags, lead score, lifecycle stage, address, social links, interests, pain points, budget, follow-up dates, custom fields); to set any of those, or to UPDATE or DELETE a contact, use fincraftly_mutate with "contacts.create" / "contacts.update" / "contacts.delete".
fincraftly_create_customerCreate a billing customer in the workspace (used when raising invoices).
fincraftly_list_invoicesList invoices in the workspace (most recent first).
fincraftly_create_invoiceCreate an invoice for a customer. The customer is matched by name/email or created if new. Provide line items as [{ description, quantity, rate }].
fincraftly_send_invoiceEmail an existing invoice to its customer (by invoice number or id). Honours the workspace approval gate — may return { held: true } awaiting a human approval.
fincraftly_send_emailSend an email through FinMail — the platform sender, or a linked mailbox you connected yourself. Honours the workspace approval gate — may return { held: true } awaiting a human approval.
fincraftly_describeThe map of everything you can do in this FinCraftly workspace. Call it with no arguments for the list of areas and what each one holds. Call it with an area (for example "dashboards", "contacts", "invoices", "workforce", "documents", "agents") for every action in that area. Call it with an action id for that action's exact input schema. Use this before fincraftly_query or fincraftly_mutate rather than guessing an action name.
fincraftly_queryRead anything in the workspace. Runs any read action from fincraftly_describe — list or fetch contacts, companies, customers, deals, products, expenses, invoices, dashboards and their cards, documents, agents, departments, employees, tasks, leads, campaigns, workflows, calls, notifications, approvals, reports, team and credits. Pagination and filters go in "query" (limit, offset, order, q); path placeholders go in "params".
fincraftly_mutateCreate, update or delete anything in the workspace. Runs any write action from fincraftly_describe — add and edit CRM records, add cards to a dashboard, edit or archive departments and AI employees, create and send invoices, write and move documents, create and run agents, start campaigns and workflows, update the org profile, and more. Call fincraftly_describe with the action id first to get its exact body schema. Deletes are real: check with fincraftly_query before removing something.
fincraftly_batchRun several FinCraftly actions in one call, in order — building a dashboard card by card, importing a list of contacts, reading four things at once. Each entry is the same shape as fincraftly_query / fincraftly_mutate. Stops at the first failure by default so a half-finished sequence does not continue on bad assumptions; set continue_on_error to run the rest anyway.