teams-api

AI-native Microsoft Teams integration — read conversations, send messages, and manage members via the Teams Chat Service REST API.

Designed for autonomous AI agents that need to interact with Teams: read messages, reply to people, monitor conversations, and participate in team workflows.

Getting Started

teams-api can be used in three ways:

1. MCP server for editors and AI tools — the recommended path for most users.

2. CLI for direct terminal use.

3. Programmatic Node.js library — advanced, documented near the end.

Prerequisites

• Node.js (v18 or later) — required for npx, which all MCP and CLI commands use.

Install in your editor

The quickest way to get started is to click one of the install badges above, or follow the instructions for your editor below.

Editor-specific instructions

Option 1 — One-click install:

Option 2 — CLI:

macOS / Linux:

# VS Code
code --add-mcp '{"name":"teams","command":"npx","args":["-y","-p","teams-api@latest","teams-api-mcp"],"env":{"TEAMS_LOGIN":"true"}}'

# VS Code Insiders
code-insiders --add-mcp '{"name":"teams","command":"npx","args":["-y","-p","teams-api@latest","teams-api-mcp"],"env":{"TEAMS_LOGIN":"true"}}'

Windows (PowerShell):

# VS Code
code --add-mcp '{"name":"teams","command":"npx","args":["-y","-p","teams-api@latest","teams-api-mcp"],"env":{"TEAMS_LOGIN":"true"}}'

# VS Code Insiders
code-insiders --add-mcp '{"name":"teams","command":"npx","args":["-y","-p","teams-api@latest","teams-api-mcp"],"env":{"TEAMS_LOGIN":"true"}}'

Windows (CMD):

rem VS Code
code --add-mcp "{\"name\":\"teams\",\"command\":\"npx\",\"args\":[\"-y\",\"-p\",\"teams-api@latest\",\"teams-api-mcp\"],\"env\":{\"TEAMS_LOGIN\":\"true\"}}"

rem VS Code Insiders
code-insiders --add-mcp "{\"name\":\"teams\",\"command\":\"npx\",\"args\":[\"-y\",\"-p\",\"teams-api@latest\",\"teams-api-mcp\"],\"env\":{\"TEAMS_LOGIN\":\"true\"}}"

Option 3 — Manual config:

Add to your VS Code MCP config (.vscode/mcp.json or User Settings):

{
  "mcpServers": {
    "teams": {
      "command": "npx",
      "args": ["-y", "-p", "teams-api@latest", "teams-api-mcp"],
      "env": {
        "TEAMS_LOGIN": "true"
      }
    }
  }
}

Or add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "teams": {
      "command": "npx",
      "args": ["-y", "-p", "teams-api@latest", "teams-api-mcp"],
      "env": {
        "TEAMS_LOGIN": "true"
      }
    }
  }
}

Add to claude_desktop_config.json (how to find it):

{
  "mcpServers": {
    "teams": {
      "command": "npx",
      "args": ["-y", "-p", "teams-api@latest", "teams-api-mcp"],
      "env": {
        "TEAMS_LOGIN": "true"
      }
    }
  }
}

claude mcp add teams -- npx -y -p teams-api@latest teams-api-mcp

Then set the environment variable TEAMS_LOGIN=true in your shell before starting Claude Code. The server will ask for your email interactively on first use.

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "teams": {
      "command": "npx",
      "args": ["-y", "-p", "teams-api@latest", "teams-api-mcp"],
      "env": {
        "TEAMS_LOGIN": "true"
      }
    }
  }
}

CLI

You can also use the CLI directly without installing anything:

npx -y -p teams-api@latest teams-api auth --login
npx -y -p teams-api@latest teams-api list-conversations --login --limit 20

If you use the CLI often, a global install is optional:

npm install -g teams-api
teams-api auth --login

Advanced Topics

Manual token usage, debug-session auth, and programmatic Node.js usage are covered later in this README.

Related MCP server: Microsoft Graph MCP

Platform support

Authentication

Most users do not need to manage tokens manually.

If you use interactive login, auto-login, or a Chrome debug session, teams-api captures the full token bundle automatically from Teams web traffic. That includes the base skypeToken plus the extra bearer tokens used for profile resolution and reliable people/chat/channel search.

Those flows also detect the Teams chat region automatically from the intercepted request URLs, so most users do not need to set --region or TEAMS_REGION.

On macOS, prefer auto-login when you have a platform authenticator / FIDO2 passkey set up. On other platforms, use interactive login.

Direct token usage is the advanced/manual path.

Auto-login (macOS only)

Requires macOS with a platform authenticator (e.g. Intune Company Portal) and a FIDO2 passkey enrolled. Fully unattended — no browser window appears.

Interactive login (recommended for Windows / Linux)

The easiest cross-platform option. A browser window opens, you log in with any method your organization supports (password, MFA, passkey, etc.), and the token is captured automatically:

teams-api auth --login

Optionally pre-fill your email:

teams-api auth --login --email you@example.com

Advanced / manual methods

Debug session — start Chrome with --remote-debugging-port=9222, navigate to Teams and log in, then run:

teams-api auth --debug-port 9222

Direct token — advanced/manual only. Extract x-skypetoken from browser DevTools (Network tab) and pass it directly:

teams-api list-conversations --token "<paste-token-here>" --region emea

If you want reliable people/chat/channel lookup and profile resolution on the direct-token path, also pass the extra bearer tokens captured from Teams requests:

teams-api find-people \
  --token "<paste-skype-token-here>" \
  --bearer-token "<paste-api-spaces-skype-bearer-token-here>" \
  --substrate-token "<paste-substrate-bearer-token-here>" \
  --region emea \
  --query "Jane Doe"

CLI

Preferred without install:

npx -y -p teams-api@latest teams-api <command> [options]

Optional global install for frequent use:

npm install -g teams-api
teams-api <command> [options]

The examples below use teams-api for readability. If you are not installing globally, replace it with npx -y -p teams-api@latest teams-api.

Auth flags (available on all commands)

Examples

# Acquire a token (interactive — all platforms)
teams-api auth --login

# Acquire a token (auto — macOS with FIDO2)
teams-api auth --auto --email you@example.com

# List conversations
teams-api list-conversations --login --limit 20 --format detailed

# Find a conversation by topic
teams-api find-conversation --auto --email you@example.com --query "Design Review"

# Find a 1:1 chat by person name
teams-api find-one-on-one --auto --email you@example.com --person-name "Jane Doe"

# Read messages (by topic name, person name, or direct ID)
teams-api get-messages --auto --email you@example.com --chat "Design Review"
teams-api get-messages --auto --email you@example.com --to "Jane Doe" --max-pages 5
teams-api get-messages --auto --email you@example.com --conversation-id "19:abc@thread.v2" --format detailed

# Newest-first order (API returns newest-first; default is oldest-first/chronological)
teams-api get-messages --auto --email you@example.com --chat "General" --order newest-first

# Send a message
teams-api send-message --auto --email you@example.com --to "Jane Doe" --content "Hello!"
teams-api send-message --auto --email you@example.com --chat "Design Review" --content "Status update"

# List members
teams-api get-members --auto --email you@example.com --chat "Design Review"

# Get current user info
teams-api whoami --auto --email you@example.com

# Export messages to a file (default format: concise)
teams-api get-messages --auto --email you@example.com --chat "General" --output exports/general.md

# Export as JSON to a file
teams-api get-messages --auto --email you@example.com --chat "General" --format detailed --output exports/general.json

MCP server

The MCP server exposes Teams operations as tools for AI agents via stdio transport. See Getting Started for editor-specific setup.

Advanced: direct token configuration

Use this only if you already have tokens from another flow or need to avoid browser-based auth entirely:

{
  "mcpServers": {
    "teams": {
      "command": "npx",
      "args": ["-y", "-p", "teams-api@latest", "teams-api-mcp"],
      "env": {
        "TEAMS_TOKEN": "<paste-skype-token-here>",
        "TEAMS_BEARER_TOKEN": "<optional-api-spaces-skype-bearer-token>",
        "TEAMS_SUBSTRATE_TOKEN": "<optional-substrate-bearer-token>",
        "TEAMS_REGION": "emea"
      }
    }
  }
}

Environment variables

Agent marker

When an AI agent sends or edits messages on behalf of a user, it can be hard to tell which messages were composed by the agent and which by the human. The TEAMS_AGENT_MARKER environment variable (or --agent-marker CLI flag / agentMarker MCP parameter) automatically prepends a configurable string to message content:

{
  "env": {
    "TEAMS_AGENT_MARKER": "Ⓜ", // or "🤖", "[Bot]", etc.
  },
}

When set, every send-message and edit-message call prepends the marker followed by a space to the content. For example, with TEAMS_AGENT_MARKER=Ⓜ, sending "Hello world" produces "Ⓜ Hello world".

The per-call parameter takes precedence over the environment variable. Pass an empty string to disable the marker for a specific call.

Edit reply guard

When editing a message that already has replies, the original context can be lost — replies may no longer make sense. The TEAMS_EDIT_REPLY_GUARD environment variable (or --reply-guard CLI flag / replyGuard MCP parameter) controls this:

The per-call parameter takes precedence over the environment variable.

Delete mode (soft-delete)

Hard-deleting messages removes content permanently, which can be problematic for auditability and conversation flow in group chats. The TEAMS_DELETE_MODE environment variable (or --delete-mode CLI flag / deleteMode MCP parameter) controls how message deletion is handled:

When using soft mode, the message content is replaced with ~~This message was removed by an agent~~ by default. Customize the tombstone text with TEAMS_DELETE_TOMBSTONE (or --delete-tombstone / deleteTombstone):

{
  "env": {
    "TEAMS_DELETE_MODE": "soft",
    "TEAMS_DELETE_TOMBSTONE": "🗑️ [removed by automation]",
  },
}

The per-call parameters take precedence over environment variables.

Audit logging

State-modifying actions (edit and delete) can emit structured audit events for compliance and traceability. The TEAMS_AUDIT_LOG environment variable controls where events are written:

{
  "env": {
    "TEAMS_AUDIT_LOG": "file:/var/log/teams-audit.jsonl",
  },
}

Each event is a single JSON line with the following fields:

Audit logging is designed to be silent — errors in the audit pipeline never affect tool execution.

Protected conversations

Some conversations contain sensitive or compliance-relevant information where accidental edits or deletions could be harmful. The TEAMS_PROTECTED_CONVERSATIONS environment variable (or --protected-conversations CLI flag / protectedConversations MCP parameter) blocks edit and delete actions in matching conversations:

{
  "env": {
    "TEAMS_PROTECTED_CONVERSATIONS": "Incident *,*compliance*,Architecture Decisions",
  },
}

Patterns are comma-separated and support * as a wildcard (matches any characters). Matching is case-insensitive. When a conversation's name matches any pattern, both edit-message and delete-message throw an error before making any changes — the message is left untouched.

The per-call parameter takes precedence over the environment variable, so individual tool invocations can override the configured patterns when needed.

Available tools

All MCP tools accept an optional format parameter (concise or detailed). Default format is concise.

Workflow guidance, tips, and important notes are served automatically via the MCP server's instructions field — no separate skill file needed. For the same content on the CLI, run teams-api guide.

Image descriptions

teams_describe_image reuses the existing Teams AMS image download support and sends the image bytes to an OpenAI-compatible vision endpoint. Configure it with TEAMS_IMAGE_DESCRIPTION_API_KEY or OPENAI_API_KEY. Optional overrides: TEAMS_IMAGE_DESCRIPTION_MODEL and TEAMS_IMAGE_DESCRIPTION_BASE_URL.

Examples:

teams-api describe-image --chat "Project Chat" --message-id 1773736076914 --image-index 0
teams-api describe-image --ams-object-id 0-eaua-d2-877b82634f4e978692f2243d445a6650

API regions

The Teams Chat Service URL varies by region. Login-based and debug-session auth detect it automatically. You only need to set --region or TEAMS_REGION when you are supplying tokens directly or want to force an override:

Known limitations

• File attachments are not supported from remote AI hosts (e.g. Claude.ai). The MCP server runs locally on your machine, so --file / --image paths must exist on your local filesystem. Cloud-hosted AI clients run in isolated containers and cannot access local paths. Use a local MCP client (Claude Desktop, Cursor, VS Code) or the CLI for file attachments.

• Token lifetime is ~24 hours. After expiry, you must re-acquire.

• The Teams Chat Service REST API is undocumented and may change without notice.

• Auto-login requires macOS, system Chrome, a platform authenticator, and a FIDO2 passkey. On other platforms, use interactive login (--login) instead.

• The members API returns empty display names for 1:1 chat participants. Use findOneOnOneConversation() to resolve names from message history.

• Reaction actor identities come from the emotions field in message payloads. Parsing handles both JSON-string and array formats.

Programmatic API

This is the advanced integration path. Most users should start with MCP or CLI instead.

Install the package in your project:

npm install teams-api

Example:

import { TeamsClient } from "teams-api";

// Interactive login — opens a browser, you log in manually (all platforms)
const client = await TeamsClient.fromInteractiveLogin();

// Or auto-login via platform authenticator (macOS + FIDO2 passkey)
const autoClient = await TeamsClient.fromAutoLogin({
  email: "you@example.com",
});

// Advanced/manual: create a client from previously captured tokens
const manualClient = TeamsClient.fromToken("skype-token-here", "emea");

const conversations = await client.listConversations();
const messages = await client.getMessages(conversations[0].id, {
  maxPages: 5,
  onProgress: (count) => console.log(`Fetched ${count} messages`),
});

await client.sendMessage(conversations[0].id, "Hello from the API!");

const oneOnOne = await client.findOneOnOneConversation("Jane Doe");
const members = await client.getMembers(conversations[0].id);

Contributing

See CONTRIBUTING.md for development setup, architecture, and implementation notes.

License

MIT