Skip to main content
Glama
MCP Microsoft Teams Server

MCP Microsoft Teams Server

by InditexTech

错误 可维护性评级 可靠性评级 GitHub 许可证GitHub 发布记分卡

MCP 团队服务器

用于Microsoft Teams集成的 MCP(模型上下文协议)服务器实现,提供阅读消息、创建消息、回复消息、提及成员的功能。

特征

https://github.com/user-attachments/assets/548a9768-1119-4a2d-bd5c-6b41069fc522

  • 在频道中发起带有标题和内容的讨论,并提及用户

  • 通过消息回复更新现有主题,提及用户

  • 阅读主题回复

  • 列出频道团队成员

  • 阅读频道消息

Related MCP server: Teams Messenger MCP App

先决条件

安装

  1. 克隆存储库:

git clone [repository-url]
cd mcp-teams-server
  1. 创建虚拟环境并安装依赖项:

uv venv
uv sync --frozen --all-extras --dev

团队配置

请阅读本文档,了解如何配置 Microsoft Teams 和所需的 Azure 资源。它并非分步指南,但可以帮助您明确所需内容。

用法

在 shell 或 .env 文件中设置以下环境变量。您可以使用示例文件作为模板:

钥匙

描述

团队应用 ID

您的 MS Entra ID 应用程序 ID 的 UUID

TEAMS_APP_密码

客户端机密

TEAMS_APP_TYPE

单租户或多租户

TEAMS_APP_TENANT_ID

如果是 SingleTenant,则租户 uuid

球队 ID

MS Teams 组 ID 或团队 ID

团队频道 ID

带有 URL 转义字符的 MS Teams 频道 ID

启动服务器:

uv run mcp-teams-server

发展

集成测试需要设置以下环境变量:

钥匙

描述

测试线程 ID

线程 ID 的时间戳

测试消息 ID

消息 ID 的时间戳

测试用户名

测试用户名

uv run pytest -m integration

预构建的docker镜像

ghcr.io 上托管了一个预构建的镜像。您可以通过运行以下命令来安装此镜像

docker pull ghcr.io/inditextech/mcp-teams-server:latest

构建docker镜像

您可以使用以下命令构建 Docker 镜像来运行 MCP 服务器:

docker build . -t inditextech/mcp-teams-server

运行docker镜像

基本运行配置:

docker run -it inditextech/mcp-teams-server

使用 .env 文件中的环境变量运行:

docker run --env-file .env -it inditextech/mcp-teams-server

设置 LLM 以使用 MCP Teams Server

请按照以下文档中的说明进行操作

变更日志

请参阅CHANGELOG.md了解变更列表和版本历史记录。

贡献

请阅读CONTRIBUTING.md了解我们的行为准则和提交拉取请求的流程的详细信息。

安全

出于安全考虑,请参阅我们的安全政策。

执照

该项目根据Apache-2.0文件获得许可,详情请见。

© 2025 INDUSTRIA DE DISEÑO TEXTIL SA (INDITEX SA)

Available Tools

6 tools
get_member_by_nameB

Get a member by its name

Inputs: name (required).

list_membersA

List all members in the team

Inputs: page_size. Returns: result

list_threadsA

List threads in channel with pagination

Inputs: limit, cursor. Returns: items, limit, total, cursor

read_threadA

Read replies in a thread

Inputs: thread_id (required), limit, cursor. Returns: items, limit, total, cursor

start_threadA

Start a new thread with a given title and content

Inputs: title (required), content (required), member_name. Returns: title, content, thread_id

update_threadB

Update an existing thread with new content

Inputs: content (required), thread_id (required), member_name. Returns: content, thread_id, message_id

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.8/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool targets a distinct resource-action pair: thread lifecycle (start/update/read/list) and member lookup (get by name/list). There is no meaningful overlap, and the descriptions make the boundary between read_thread and list_threads clear.

    Naming Consistency5/5

    All tools follow a consistent snake_case verb_noun pattern such as start_, update_, read_, list_, and get_. The verb choices are predictable and match the operation being performed.

    Tool Count5/5

    Six tools is well-scoped for a Teams server covering thread management and member lookup. There are no redundant tools, and the set feels appropriately sized for its stated domain.

    Completeness4/5

    Threads have start, read, update, and list coverage, while members have get and list coverage. Missing thread deletion and explicit reply/send-message operations are minor gaps, but the core workflows agents would likely need are covered.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that bridges Microsoft Teams and MCP-compatible clients, enabling chat integration, message handling, and advanced search capabilities without REST API endpoints.
      1
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that bridges Microsoft Teams with MCP-compatible clients (LLMs, agentic frameworks, CLI), enabling chat integration, message search, and event streaming without traditional REST API endpoints.
      -