Official Connector

Flusia CRM · MCP Server

Connect Flusia CRM to Model Context Protocol–compatible AI assistants: Claude.ai, Claude Desktop, Claude Code, ChatGPT Connectors and the Claude mobile app.

MCP endpoint:https://api.flusia.it/mcp
Version:1.0.0

1. What it is

In plain words: by connecting Flusia to your AI assistant (for example Claude or ChatGPT) you can ask it, in everyday language, to look up data, prepare a report or create activities in the CRM. You switch the connection on and off yourself, and the assistant can only do what your permissions allow.

The Flusia MCP server (the technical “bridge” that makes the connection possible) lets the assistant work with CRM leads, quotes, tasks, projects, invoices, newsletters and WhatsApp chats through the tools authorized for the connection.

Available tools depend on the service configuration and the permissions of your Flusia connection. Review which actions you authorize when connecting your assistant.

2. Features and use cases

Examples of CRM areas the assistant can work on, subject to connection permissions. The “Tool prefix” column is the technical name developers see: you can ignore it.

ResourceTool prefixCapability
Leads / Clientscrm_clients_*Create, read, update, delete, search, related quotes, notes, recordings
Quotescrm_deals_*Create, read, update, delete, status, services, contacts, commissions, notes
Taskscrm_tasks_*Create, read, update, delete, checklist, attachments, tags, assignment
Projectscrm_projects_*Create, read, update, delete, brief, activities, archive, assignments
Activitiescrm_activities_*Timeline of calls, meetings, emails, notes
Servicescrm_services_*Service/product catalog
Pipelinescrm_pipelines_*Pipelines and sales stages
Invoicescrm_invoices_*Read Fatture in Cloud invoices, allocation, queue
Newslettercrm_newsletter_*Lists, email campaigns, blacklist, quota, domains
WhatsAppcrm_whatsapp_*Chats, messages, notes, with each user limited to the chats they can access
QR Codescrm_qr_codes_*Generate and manage QR tracking
Wikicrm_wiki_*Organization knowledge base
Workflowcrm_workflows_*Automation steps and triggers
Settingscrm_settings_*Company settings (users, roles, templates)
Statscrm_stats_*Key indicators and revenue analysis

Each tool tells the assistant whether it only reads or whether it can modify or delete data.

Typical use cases

  • Sales assistant in conversation: search leads, update status, create follow-up tasks, send WhatsApp messages.
  • Reports from a request written in everyday language (“Summary of quotes won this week for pipeline X”).
  • CRM data operations: review proposed actions and your assistant’s confirmation settings before authorizing them.
  • Starting a new customer: lead, quote, task and checklist in a single conversation.
  • Checks: the assistant looks at the CRM state to understand anomalies reported by the team.

3. How to connect

Claude.ai (web)

  1. Go to claude.ai and open Customize → Connectors → Add
  2. Name: "Flusia CRM"
  3. Server URL: https://api.flusia.it/mcp
  4. Confirm. On first use Claude will start the OAuth flow.
The Claude "Add custom connector" dialog with the Flusia MCP server URL
In Claude: Customize → Connectors → Add. Any name, URL https://api.flusia.it/mcp.

ChatGPT

On ChatGPT web, Business and Enterprise/Edu support full MCP; Pro supports read-only connections. Add the MCP server from Plugins; enabling developer mode first is not required. Workspace permissions determine availability and allowed actions.

Official OpenAI requirements and setup

4. Usage examples

Example 1: create a lead by writing in everyday language

User request (example)

"Create a new lead called Studio Dentistico Bianchi, VAT 12345678901, based in Milan at Via Roma 10, and assign the opportunity to Mario Rossi. Add a follow-up task to call him tomorrow."

Steps the assistant takes (example)
  1. crm_users_list (search Mario Rossi → obtains user_id)
  2. crm_clients_create_lead with business_name, vat_number, address, assigned_to
  3. crm_tasks_create with client_id of the new lead, due_date = tomorrow
Answer (example)
The AI confirms with the 2 created IDs and a verbal summary.

Example 2: report of quotes won last month

User request (example)

"Which quotes did we close as won last month? Show total revenue and the top 3 by value."

Steps the assistant takes (example)
  1. crm_stats_revenue with start_date and end_date → returns total revenue and win rate
  2. crm_deals_list with status: "accepted", limit: 50
  3. The assistant sorts the results and prepares a table and indicators
Answer (example)
Example with made-up figures.
Revenue closed last month: €127,430
Win rate: 34%
Top 3 quotes: ACME Corp €45,000, Studio Verdi €28,500, TechStart €19,800

Example 3: data cleanup with confirmation

User request (example)

"Delete all duplicate leads of ‘Mario Rossi’ with the same VAT number."

Steps the assistant takes (example)
  1. crm_clients_search with q: "Mario Rossi" → candidates
  2. The assistant spots the duplicate VAT numbers
  3. The assistant asks the user for explicit confirmation, because crm_clients_delete is flagged as an action that deletes data
  4. Only after confirmation it runs crm_clients_delete
Answer (example)
Example: the user sees the confirmation request for each operation and, at the end, a summary of what was done.

Tools that delete or cancel data (delete, remove, cancel, archive, unassign) are flagged as “destructive” (destructiveHint: true). In these cases the assistant must first ask for your confirmation: this is the “human-in-the-loop” principle, meaning a person always has the final say.

5. Privacy and data protection

Data processing follows:

What flows through MCP

  • Only what the assistant actually asks for: ask about stalled quotes and only those travel, nothing else
  • Whatever the assistant receives lands in your conversation with it, so it is processed by its provider (Anthropic for Claude, OpenAI for ChatGPT) under the terms you accepted with them: they are US companies, and that holds even though your Flusia stays in Europe
  • You turn the connection on and you can turn it off at any time: until you connect it, nothing leaves the CRM
  • We keep a trace of each request for 30 days, without storing its content

What does NOT flow through

  • The Flusia server does not receive the conversation between you and the assistant, only the requests of the tools the assistant chooses to use
  • The assistant provider (Anthropic or OpenAI) sees the responses inside the conversation, but has no direct access to the Flusia database

6. Support

Technical supportsupport@flusia.it
Security / vulnerabilitiessecurity@flusia.it
Privacy / GDPRprivacy@flusia.it
Status pagehttps://status.flusia.it
User documentation/wiki

Response times: first reply within 24 business hours for standard support; confirmed security reports are handled with priority.

Ready to connect your CRM to your AI assistant?

Create a Flusia account, check your assistant’s requirements and follow the steps to authorize the connection.