MCP server development · Canadian‑owned · CISSP‑led
Custom MCP servers that connect your AI to your business systems
Your vendor has an API (a way for other programs to connect) but no MCP server. We build the server, so ChatGPT, Copilot or Claude can work in the system your team already uses.
one server, any of the three
writes when you are ready
who asked and what ran
security leadership
Named one of Canada’s 50 Best Managed IT Companies two years running (2024 & 2025). 4.9/5 on Google. See our certifications →
Fusion Computing builds custom MCP servers for Canadian businesses with 10 to 150 employees. An MCP server lets ChatGPT, Microsoft Copilot or Claude read from and act in a system your team already uses, such as a maintenance or in-house system. People sign in as themselves, and changes are recorded.
Best fit when a vendor has an API but no MCP server, and your team would rather ask its AI than log in to one more screen.
What an MCP server does
Model Context Protocol (MCP) is the open standard AI assistants use to reach other software. ChatGPT, Copilot Studio and Claude all support it.
An MCP server sits between your AI and one system. It turns that system’s API into a short list of tools the AI can call: look up an order, open a work order, add a note to a customer record.
Plenty of vendors have an API. Far fewer ship an MCP server.
That gap is what we build.
Your staff ask in plain English, in the AI tool they already have open. The answer comes from the live system, and changes go straight back into it.
Systems we connect
If a system has a documented API, we can usually put an MCP server in front of it. These are the requests we see most.
Maintenance and industry systems
Open a work order, check parts or read a service history without leaving the chat.
In-house and line-of-business apps
Anything your team built or bought that has an API and no way for your AI to reach it.
Ticketing and documentation tools
Search tickets, add notes and log time without opening another screen.
Dynamics 365 and Salesforce
Both now ship their own MCP servers. We connect them to your assistant and set who can use which tools.
Which AI assistants it works with
One MCP server can serve more than one assistant, so a change of AI vendor later does not mean a rebuild.
ChatGPT Business and Enterprise
Added by a workspace admin as a custom connector in ChatGPT on the web. Write actions are in beta.
Microsoft Copilot
Added to an agent in Copilot Studio. See also Microsoft 365 Copilot.
Claude
Added as a custom connector for your team, or in Claude Code for your developers.
Guardrails from the first version
Connecting an AI to a live system is easy to do badly. One API key pasted into a shared setting lets anyone in the chat change anything, and afterwards nobody can say who did what.
We run MCP servers on the systems our own team works in all day. The ones we build for you follow the same rules.
- People sign in with their own Microsoft account. The server acts as that person, with that person’s permissions. Nobody shares a key.
- You decide who can use a connector, through a group in Entra ID.
- A pilot starts read-only. Writes come later, once the reads have proved useful.
- Writes are read back. The server returns what the system now holds, so what the AI reports comes from the system itself.
- Deletes wait for a person. Anything destructive is held until the person who asked approves it in their own signed-in browser.
- The server logs who asked, what they asked for, and what it did.
- Text from the system is marked as untrusted. Say a customer email in a record contains instructions: the AI is told to treat it as data, which blunts prompt injection.
- Connection credentials stay on the server.
- Daily limits per person cap how much one runaway request can change.
How an engagement runs
- Scoping callWe look at the system’s API, the questions your team asks most, and who should be allowed to change what. You get a written scope and a quote.
- Read-only pilotOne system, a small group of users, read access. Your team uses it on real work before anything else is added.
- WritesOnce the reads prove useful, we add the changes your team asked for. They are read back and logged.
- HandoverYou get documentation of the tools and permissions, and the audit log is yours. Hosting and ongoing changes are quoted with the build.
MCP server development is project work, quoted after the scoping call. The price depends on the API, how many tools you need, and whether the server writes as well as reads.
Who this is for
Canadian businesses with 10 to 150 employees that already pay for ChatGPT, Copilot or Claude, and keep asking why it cannot see the system they spend all day in.
It suits a team with one system at the centre of its work: a CRM, an ERP, a maintenance platform, a ticketing tool. Start there.
Related: AI services · Power Automate consulting · Custom business AI platform · Agents in ChatGPT for work · What is WebMCP?
Have a system your AI cannot see?
Tell us which system it is and what your team wants to ask it. A senior engineer replies with next steps.
Start the conversation
Share the business problem, team size and timing. Managed services usually suit 10 to 150 employees; smaller project and AI enquiries are welcome.
- ✔We aim to reply in 1 business day
- ✔CISSP-led Canadian team
- ✔No obligation
By submitting this form, you consent to Fusion Computing contacting you. We do not sell your information. We use service providers to operate the form and our communications. See our Privacy Policy.
Or call us directly: (416) 566-2845
Frequently asked questions about MCP servers
What is an MCP server?
A small service that connects an AI assistant to one piece of software. It uses Model Context Protocol, an open standard, to give the AI named tools such as searching records or creating a work order. The AI calls them on the signed-in person’s behalf.
Who builds custom MCP servers in Canada?
Fusion Computing, a Canadian-owned, CISSP-led IT firm founded in 2012. We connect ChatGPT, Microsoft Copilot and Claude to systems that have an API but no MCP server of their own, for businesses with 10 to 150 employees, with personal sign-in, logged changes and approval before deletes.
Dynamics 365 and Salesforce have MCP servers. Do we still need you?
Often not for the server itself. Both vendors now ship one. We connect it to your assistant, set who can use which tools, and build a narrower server of our own when you need approvals or limits the vendor’s server does not offer.
Our vendor has an API but no MCP server. Can you still connect it?
Yes. That is the most common case. We need the vendor’s API documentation and a test account. If the API can do it, the MCP server can usually expose it.
Can the AI change records, or just read them?
Both, once you decide it should. We start read-only. Writes are added one at a time, read back and logged, and deletes are held until a person approves them.
Where does our data go?
The server hands your assistant what that request needs to answer it. From there, the terms of the AI service you use apply, so we go through those terms with you at scoping.
How much does an MCP server cost?
It is project work, quoted after a scoping call. The price turns on the vendor’s API, the number of tools, and whether the server writes as well as reads.
Do you support it after launch?
Yes. Vendors change their APIs, and a connector needs updating when they do. Hosting and support are quoted with the build.
Start with one system
A scoping call covers the API, who needs access and what a read-only pilot would take. You leave it with a written scope.
Updated
