The Company Formation MCP for AI coding tools. Form companies, manage bank accounts, cards, invoices, and more — directly from your terminal.
npm install -g lovielovie loginThis opens your browser to authenticate with your Lovie account.
Claude Code
To add Lovie globally (available in all projects):
claude mcp add --scope user lovie npx lovieTo add Lovie to the current project only:
claude mcp add lovie npx lovieCursor — add to .cursor/mcp.json
{
"mcpServers": {
"lovie": {
"command": "npx",
"args": ["-y", "lovie"]
}
}
}Windsurf — add to mcp_config.json
{
"mcpServers": {
"lovie": {
"command": "npx",
"args": ["-y", "lovie"]
}
}
}Claude Desktop — add to claude_desktop_config.json
{
"mcpServers": {
"lovie": {
"command": "npx",
"args": ["-y", "lovie"]
}
}
}VS Code / GitHub Copilot — add to .vscode/mcp.json
{
"mcpServers": {
"lovie": {
"command": "npx",
"args": ["-y", "lovie"]
}
}
}Replit — add to .replit or use the MCP panel in Replit Agent
{
"mcpServers": {
"lovie": {
"command": "npx",
"args": ["-y", "lovie"]
}
}
}Lovable — in the MCP integration settings, add:
Name: lovie
Command: npx
Arguments: -y lovie
Manus — in the MCP tool configuration, add:
Name: lovie
Command: npx
Arguments: -y lovie
OpenAI (ChatGPT / Codex) — if MCP is supported, use the same stdio config:
{
"mcpServers": {
"lovie": {
"command": "npx",
"args": ["-y", "lovie"]
}
}
}Any MCP-compatible platform — Lovie works with any tool that supports the MCP stdio protocol. Use npx -y lovie as the command, or lovie if installed globally.
That's it. Your AI tool now has access to 79 Lovie business tools.
Related MCP server: companylens-mcp
Category | Tools |
Company Formation | Start formation, set state, choose entity type, check name availability, add shareholders, generate certificate, pay filing fee |
Bank Accounts | Create checking/savings/wallet, get balances, freeze/unfreeze, close accounts |
Cards | Issue virtual/physical cards, set spending limits, freeze/unfreeze, cancel |
Payments | Transfer between accounts, deposit funds, withdraw from wallet |
Invoicing | Create/send/duplicate invoices, mark as paid, generate PDFs |
Clients | Create and manage client records for invoicing |
Transactions | List and filter transactions with AI-powered categorization |
Linked Accounts | Connect external bank accounts via Plaid, sync transactions |
User Profile | View/update profile, manage sessions, activity history |
lovie # Show setup instructions
lovie login # Authenticate with Lovie
lovie logout # Clear stored credentials
lovie status # Check authentication status
lovie help # Show helpThis package is a lightweight stdio-to-HTTP proxy. It connects your local AI tool to the Lovie MCP server:
AI Tool (Claude, Cursor, etc.) ←— stdio —→ lovie (this package) ←— HTTPS —→ Lovie MCP ServerOn startup, discovers all available tools from the remote server
Forwards tool calls over HTTPS and returns results via stdio
Handles OAuth authentication, session management, and automatic token refresh
All business logic runs on the Lovie server — this package is just the bridge
Variable | Description |
| Custom MCP server URL (default: |
| Bearer token — overrides stored OAuth token |
| Enable verbose logging to stderr |
Node.js 18+
A Lovie account (lovie.co)
MIT
The user is not authenticated with Lovie. Tell them to run npx lovie login in their terminal to authenticate, then restart the MCP connection. All Lovie tools (company formation, banking, cards, invoices) will become available after login.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It clearly describes the tool's informational behavior and the required user action. It does not disclose any side effects, but for a simple notification tool, this is sufficient. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise—two sentences—and front-loaded with the key message. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and a simple informational purpose, the description is complete. It tells the user exactly what to do and what to expect.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are zero parameters, and schema coverage is 100%. Per guidelines, baseline is 4. The description does not add parameter info, but none is needed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool's purpose: to indicate that the user is not authenticated and to provide a specific command to authenticate. It specifies the action and outcome.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly tells when to use the tool (when user is not authenticated) and what the user should do (run `npx lovie login`). It also explains the result: all Lovie tools become available after login. No sibling tools exist, so differentiation is not needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.9lovie_auth_requiredScored across 1 tool
While there is only one tool, its purpose (requiring authentication) is fundamentally different from the server's claimed domain (company formation). This creates confusion about what the server actually does.
The tool name 'lovie_auth_required' does not follow a verb_noun pattern and is more descriptive of a state than an action. With only one tool, no consistent naming pattern is established.
A single tool claiming to be for company formation is far too few. The tool merely acts as an authentication gate, not a functional capability.
The tool surface is severely incomplete for company formation. No tools for company creation, banking, invoicing, etc. are actually provided despite the server name.
CompanyLens is a remote MCP server giving AI agents instant access to official company registry data across 19 jurisdictions in Europe, the Americas, and Asia-Pacific. Eighteen read-only tools let you search companies and people, look up officers and beneficial owners, map corporate networks through shared directors, screen names against the UK disqualified directors register, find every company at a registered address, and pull filing history — all from a single connector. Visit our website: https://companylens.io
AI voice agents on SMB websites — fully autonomous build in 2–3 min. 23 MCP tools. EU, GDPR.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
Invoicing you drive by talking to your AI: log time, raise invoices and track what's owed via MCP.
