Connect Segment to Microsoft Copilot via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Twilio Segment, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Twilio Segment + Microsoft Copilot

Let your AI work with your Twilio Segment workspace: list sources, destinations and warehouses, check event volume, delivery and warehouse syncs, read tracking plans, Functions, usage and the audit trail. US and EU workspaces.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

SEGMENT_API_HOST, SEGMENT_API_TOKEN

Step 1 — Get credentials

1. As a Workspace Owner, open Settings → Workspace settings → Access Management → Tokens (https://app.segment.com/goto-my-workspace/settings/access-management/tokens) and click Create Token.
2. Choose a Public API token, not a Config API token. Give it the smallest role that covers what you need: Workspace Member with read-only roles (for example Source Read-only and Tracking Plan Read-only) for reading, Workspace Owner only if the write tools will be switched on.
3. Segment shows the token once: copy it into SEGMENT_API_TOKEN straight away. It is sent as a Bearer token and only to Segment.
4. Set SEGMENT_API_HOST to the workspace's region: https://api.segmentapis.com for a US workspace, https://eu1.api.segmentapis.com for an EU workspace. A token only works in its own region.
5. Install the connector and run segment_get_workspace to check the connection. A token belongs to one workspace, so install one connector per workspace.

What it reads: sources, destinations with their Actions mappings, warehouses with their connection state and recent syncs, event volume over time, Delivery Overview (where events are dropped, step by step, with discard reasons), delivery metrics per destination, tracking plans and their rules (Protocols), Functions with their code, daily API call and MTU usage, and the Audit Trail of who changed what. Tracking plans need Protocols, Functions need the Functions feature, and mappings need Destination Subscriptions in the workspace.

Secrets: settings fields that usually hold the credentials of destinations and warehouses (API keys, secrets, tokens, passwords) are left out. segment_get_source does return the source's write keys, which let anyone send data into that source.

Limits: Segment limits requests per token, IP address and endpoint, and answers 429 with a Retry-After header. Some endpoints are stricter: warehouse syncs allow 2 calls a minute, event volume 60 a minute, tracking plan rules and warehouse connection state 200 a minute. Lists come in pages of up to 1,000 items, and the AI follows pagination.next until it has everything.

Switched off at install: segment_update_source and segment_update_destination rename a source or destination or switch it on or off, and a disabled one drops data until it is enabled again. segment_delete_source and segment_delete_destination cannot be undone. An administrator turns these tools on deliberately, and even then the AI confirms each change with you first; a delete waits until you confirm the id and name.

Common errors: 403 "Not authorized to perform this operation": the token is wrong or revoked, belongs to a workspace in the other region, is a Config API token, or its role does not cover this resource. 401: no token was sent. 404: there is no resource with that id in this workspace. 422: a parameter is missing or invalid, for example a Delivery Overview time range longer than its granularity allows. A message about a feature means the workspace has no Protocols, Functions or Destination Subscriptions. 429: wait for the time in Retry-After.

The connector does not send events: Segment's Tracking API uses a source's write key on a different host. It does not create sources, destinations or warehouses either, and does not cover filters, transformations, Reverse ETL, Engage audiences and computed traits, access management, deletion and suppression regulations or the catalog.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Microsoft 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.

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 Twilio Segment 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.

Available tools

Example prompts

• "Which of our destinations are disabled, and which sources do they read from?"
• "Show me the Delivery Overview of our iOS source for the last 24 hours and where events were dropped."
• "How did event volume develop per source over the last 7 days, and how many MTUs have we used so far this month?"
• "Who changed sources or destinations in the last two weeks, according to the audit trail?"

FAQ

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.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT
• Connect to Cursor
• Connect to Gemini
• Connect to Meta Muse