Short answer
In Copilot Studio, open your agent, then Tools, Add a tool, New tool, Model Context Protocol. Name it, describe when the agent should use it, enter the MCP server's address and choose OAuth 2.0 with dynamic discovery so each person signs in as themselves. Add it to the agent and publish to Teams and Microsoft 365 Copilot. With Fieldproxy's server, your team can then ask Teams about jobs, SLAs and schedules and act on them with a confirm step.
Add Fieldproxy's MCP server to Copilot Studio
- 1
Open Tools
In your Copilot Studio agent, open Tools, Add a tool, New tool, Model Context Protocol.
- 2
Describe it
Name it Fieldproxy and write a one-line description, for example "Field service jobs, schedules, customers and invoices". The agent uses it to decide when to call Fieldproxy.
- 3
Enter the address
Use your region's Fieldproxy MCP address, for example https://api-us-east-1.fieldproxy.ai/mcp.
- 4
Choose authentication
OAuth 2.0 with dynamic discovery, so each person signs in with their own Fieldproxy account. Or an API key in the Authorization header.
- 5
Publish
Create the connection, add it to the agent, and publish to Teams and Microsoft 365 Copilot.
Before you start
You need a Copilot Studio licence from Microsoft, and your Power Platform data policy must allow the connection. On the Fieldproxy side, AI assistant access must be switched on for the workspace.
What your team can ask in Teams
- "Which P1 jobs are at risk of missing SLA today?"
- "Summarise everything that happened on the hospital contract this week."
- "Who is free near the Westfield site this afternoon?"
Fieldproxy facts on this page come from the Fieldproxy MCP reference. Competitor details are from each vendor's own documentation as of September 27, 2026; see the comparison table and sources.