Helios iNuvio can answer almost anything \u2014 the answer is just buried in a report that someone has to find, configure and run. A typical management question (“who owes us the longest?”, “what is our margin on this job?”) therefore ends up with the one person who knows Helios well. Since Claude and ChatGPT gained support for custom connectors, there is a second route: ask in plain language and let the number be pulled straight from your ERP. This article covers what you need and where the limits are.<\/p>\n
You need three things: a paid Claude account, access to your Helios data (by default read straight from the database) and an MCP server in between.<\/strong> The connection itself is one entry in the settings and one sign-in. The slow part is the boring one \u2014 arranging secure access to the data, which is a job for your IT team and takes days, not months. Read-only is the safe default; writing is enabled separately and every action is confirmed by a person.<\/strong><\/p>\n<\/div>\n The MCP (Model Context Protocol)<\/a> standard comes from Anthropic, the maker of Claude \u2014 which is why connectors have been working here longest and most reliably. It is not exclusive, though: the same server also works from ChatGPT, and Microsoft is adding support too. The practical difference lies elsewhere: custom connectors are part of the paid plans (Claude Pro or Team), and for a company Team makes sense, because connectors and access are managed centrally rather than person by person.<\/p>\n It pays off fastest wherever people currently wait for someone else. Accounting<\/strong> asks for the VAT return figures for a period, or for purchase invoices due this week. Sales<\/strong> pulls a customer’s history and payment record before a meeting without having to ask anyone. The warehouse<\/strong> checks availability, reservations and items below minimum. Management<\/strong> asks about turnover by cost centre, partner balances and a cash-flow outlook based on due dates. The higher tier adds write actions \u2014 a draft invoice, a new order or contact \u2014 but always so that you confirm the result before it is saved, and they go through the vendor’s official interface rather than writing to the database.<\/p>\n AI over an ERP is not a replacement for integration. If orders from your e-shop need to land in Helios reliably every few minutes, including at three in the morning, that is a job for a classic system-to-system connection<\/a>, not for a conversation. MCP connects people to data; integration connects systems to each other. Most companies end up using both, for different purposes.<\/p>\n<\/div>\n Before you get into AI, be clear about which Helios you actually have \u2014 Asseco has renamed the range several times and quotes still get it confused. Helios Orange<\/strong> was renamed Helios iNuvio<\/strong>, and Helios Green<\/strong> became Helios Nephrite<\/strong>; these are two separate product lines for companies of different sizes, not versions of one. For connecting AI, what matters is where the data sits and who is allowed in: both lines run on SQL Server, so the standard route is reading with a dedicated account that has read-only rights \u2014 the paid eServer module is not needed for that. If you have the Helios REST API available, we can connect through it instead and never touch the database. Writing always goes through the vendor’s official interface; check the availability and price of eServer with your supplier, as the price list is not public. What each generation can do when connecting other systems<\/a> is covered on the system page.<\/p>\n You do not have to choose. MCP is an open standard and the same server serves both \u2014 in ChatGPT you add a connector under Settings \u2192 Connectors, in Claude under Settings \u2192 Connectors; the difference is practically just the button label. If your company already pays for one, start there. The procedure for POHODA, identical in the details, is described in How to connect Claude to POHODA<\/a>.<\/p>\n The full checklist is covered in Security of AI over company data<\/a>; how we handle it is described on our security model page<\/a>.<\/p>\n Queries are optimised for reading and run at low priority \u2014 a typical question is a fraction of the load of an ordinary report. Limits are set during deployment.<\/p>\n<\/details>\n Not for reading \u2014 a dedicated read-only account on the database is enough, and neither the paid eServer module nor the REST API is required. If you do have the REST API available, we can use it too. Write actions (issuing an invoice, creating an order) always go through the vendor’s official interface; check eServer availability and pricing with your Helios supplier, as the price list is not public.<\/p>\n<\/details>\n No. The scope is set per area and only what you allow applies \u2014 typically receivables, orders, stock and accounting summaries. Sensitive areas, payroll above all, are usually not exposed at all.<\/p>\n<\/details>\n Your AI subscription (Claude, ChatGPT) stays yours and you pay for it directly. On top of that comes access to your data \u2014 from \u20ac99 per month excl. VAT per company for the read tier, \u20ac199 with writing, plus a one-off implementation from \u20ac800 covering secure access, area configuration and training. Details are on the Helios iNuvio MCP<\/a> page.<\/p>\n<\/details>\n Yes, the principle is the same \u2014 both lines run on SQL Server. The data model and the range of areas differ, so they are mapped differently during deployment; we go through the exact scope on the introductory call.<\/p>\n<\/details>\n","protected":false},"excerpt":{"rendered":" Helios keeps its data in SQL Server and its answers in reports someone has to run. With an MCP server you can ask for them in plain language, straight from Claude. What you need, how the connection works and where the limits are.<\/p>\n","protected":false},"author":0,"featured_media":72097,"template":"","erpedie-topic":[],"class_list":["post-72104","erpedie","type-erpedie","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/symmy.com\/en\/wp-json\/wp\/v2\/erpedie\/72104","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/symmy.com\/en\/wp-json\/wp\/v2\/erpedie"}],"about":[{"href":"https:\/\/symmy.com\/en\/wp-json\/wp\/v2\/types\/erpedie"}],"version-history":[{"count":2,"href":"https:\/\/symmy.com\/en\/wp-json\/wp\/v2\/erpedie\/72104\/revisions"}],"predecessor-version":[{"id":72116,"href":"https:\/\/symmy.com\/en\/wp-json\/wp\/v2\/erpedie\/72104\/revisions\/72116"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/symmy.com\/en\/wp-json\/wp\/v2\/media\/72097"}],"wp:attachment":[{"href":"https:\/\/symmy.com\/en\/wp-json\/wp\/v2\/media?parent=72104"}],"wp:term":[{"taxonomy":"erpedie-topic","embeddable":true,"href":"https:\/\/symmy.com\/en\/wp-json\/wp\/v2\/erpedie-topic?post=72104"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Why Claude<\/h2>\n
What you will need<\/h2>\n
\n
Connecting in three steps<\/h2>\n
\n
https:\/\/mcp.symmy.ai\/helios<\/code>) and sign in. It uses OAuth, so no Helios password or shared keys ever go into Claude.<\/li>\nWhat Claude can do over Helios<\/h2>\n
Where it will not help<\/h2>\n
Helios Orange, iNuvio, Green and Nephrite: what it will actually run on<\/h2>\n
Claude or ChatGPT?<\/h2>\n
Security: four questions before you go live<\/h2>\n
\n
Frequently asked questions<\/h2>\n
Will it slow Helios down for everyone else?<\/summary>\n
Do we need the eServer module?<\/summary>\n
Will the AI see every piece of data in the ERP?<\/summary>\n
What does it cost?<\/summary>\n
Does it work with Helios Nephrite (formerly Green)?<\/summary>\n