How to Use Jev in Microsoft Copilot: TypeSafe's Decision Model as a Connector

Jev in Copilot

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Short answer: install the Jev connector on AnythingMCP with your TypeSafe API key, then add AnythingMCP to a Copilot Studio agent as an MCP tool (Tools → Add a tool → New tool → Model Context Protocol, URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID). From then on Copilot can ask Jev whenever it needs a quick, measurable judgment: is this urgent, which category, how good a fit, and gets a probability back instead of guessing.

Copilot is good at reasoning and writing; Jev is built for the narrow decisions in between. It answers yes/no, choice and score questions with calibrated probabilities in about 300 ms and at a fraction of the cost of a chat model. Copilot decides what to ask and what to do with the answer.

Set it up

Step 1: Install Jev on AnythingMCP

1. Create an API key at console.typesafe.ai.
2. Create a workspace on AnythingMCP Cloud (7 days free) or use your self-hosted AnythingMCP.
3. Open Connectors, find Jev by TypeSafe, click Install and paste the key into TYPESAFE_API_KEY.

Step 2: Add AnythingMCP to Microsoft Copilot

Microsoft Copilot uses MCP servers through agents built in Copilot Studio: you add AnythingMCP to an agent as a tool, then publish the agent to Microsoft 365 Copilot and Teams. Copilot Studio connects from Microsoft's cloud over Streamable HTTP, which AnythingMCP supports.

1. In Copilot Studio, open your agent (or create one), go to Tools and choose Add a tool → New tool → Model Context Protocol.
2. Enter a Server name (for example AnythingMCP), a Server description that says what the connector does, and the Server URL https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID. Copilot Studio uses the description to decide when to call the server.
3. Under authentication, choose API key, set Type to Header and the header name to X-API-Key, then select Create.
4. In Add tool, choose Create a new connection, paste an MCP API key from AnythingMCP (MCP Servers → your server → API keys) and select Add to agent.
5. Try it in the agent's Test pane: ask for something that needs the Jev tools.
6. Select Publish, then Channels → Microsoft 365 and Microsoft Teams, keep Make agent available in Microsoft Copilot selected and choose Add channel. See agent in Teams installs it for you; in Microsoft 365 Copilot, type @ and pick the agent.

Prefer per-user sign-in? Choose OAuth 2.0 → Dynamic discovery instead of an API key: each user then signs in to AnythingMCP the first time the agent calls it.

Self-hosting? Use your instance's public HTTPS address instead of https://cloud.anythingmcp.com. Copilot Studio connects from Microsoft's cloud, so localhost does not work.

Step 3: Ask Copilot to use Jev

Start a new chat and mention Jev in the request, for example "use Jev to decide which of these tickets are urgent". Copilot reads jev_playbook first and then calls the Jev tools on its own.

What happens when you ask

Say you paste ten customer emails and ask which need a reply today. Copilot builds one yes/no question ("Does email ask for something that blocks the customer today?"), calls jev_yes_no or jev_ask for each email with the email text as evidence, and gets back a probability per email. It then sorts them, shows you the clear cases and names the ones between 0.15 and 0.85 as unsure, instead of pretending to be certain.

For a real run with four tickets, including one in German, see the Jev overview.

Prompts to try in Copilot

• "Use Jev to sort these support tickets into billing, technical, sales or none, and show the probabilities."
• "Ask Jev which of these 15 job applications match the requirements below, and list only the ones above 0.8."
• "Rate each of these product reviews from 0 (angry) to 3 (delighted) with Jev and summarise the angry ones."
• "Before I send this reply, ask Jev whether it answers every question in the customer's email."
• "Use Jev to check whether these two supplier records are the same company."

Good to know

• Jev returns numbers, not explanations. Ask Copilot to split a borderline case into smaller yes/no questions if you want to see why.
• Copilot and Jev both read your text: the evidence for each question is sent to TypeSafe as the question's state.
• The TypeSafe key stays on the AnythingMCP server, encrypted. People on your team connect with their own login and never see it.

Question types, costs and every limit in detail: Jev MCP server overview.

FAQ

Is Jev replacing Copilot? No. Jev cannot write text. Copilot keeps the conversation, the reasoning and the answer; Jev handles the yes/no, choice and score calls where a probability is more useful than a paragraph.

Which languages does Jev understand? English best. German and Italian tickets came back correct and confident in our tests; for other languages, watch the confidence values.

Which Copilot is this for? Microsoft 365 Copilot at work, through agents built in Copilot Studio. The Microsoft Copilot app for personal accounts has no option to add your own MCP server.

What do I need? A work account with access to Copilot Studio (a license or a trial) to build the agent. People who use it in Microsoft 365 Copilot or Teams need access to the agent: share it with them, or ask an admin to publish it to the organization. If your organization applies data policies to Power Platform connectors, they cover MCP servers too.

The agent doesn't call the tools. Check that the header name is exactly X-API-Key and that the key belongs to the same MCP server as the URL, and make the server description specific: Copilot Studio uses it to decide when to call the server. Publish the agent again after each change; in an open chat, type "start over" to get the new version.

Related

• Jev MCP server: the overview
• Triage support tickets with Jev in Claude
• Connect Jev to Claude
• Connect Jev to ChatGPT
• Connect Jev to Cursor
• Connect Jev to Gemini
• Connect Jev to Meta Muse
• Jev by TypeSafe in the marketplace