home / mcp / microsoft teams mcp server

Microsoft Teams MCP Server

This read-only MCP Server allows you to connect to Microsoft Teams data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-microsoft-teams-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/microsoft-teams.prp"
      ]
    }
  }
}

This MCP server lets you query live Microsoft Teams data through a simple MCP interface. It wraps the CData JDBC Driver for Teams, exposing Teams data in a read-only MCP endpoint so large language models can fetch up-to-date information by asking natural-language questions without writing SQL.

How to use

You run the MCP server locally and connect your AI client to it. The server operates via standard input/output (stdio) on the machine where you start it, so use an AI client that runs on the same device. Once running, your AI client can ask questions like which opportunities are open, counts of calendar events today, or any other data exposed by the driver. Use the built-in tools to read data and retrieve available tables, columns, and run queries through natural language prompts.

You don’t need to call the tools directly. Simply ask your AI client to fetch information, and it will use the MCP server to read the underlying data source. For example, ask about tables you can access, then query specific columns, or run a SELECT query through the tool interface if your client supports it.

How to install

Prerequisites: make sure you have Java Runtime Environment 8+ and Maven installed on your machine.

1. Clone the project and enter the directory.

git clone https://github.com/cdatasoftware/microsoft-teams-mcp-server-by-cdata.git
cd microsoft-teams-mcp-server-by-cdata

2. Build the MCP server to produce the JAR file.

mvn clean install

3. Download and install the CData JDBC Driver for Microsoft Teams, then license it.

4. Configure your JDBC connection using the driver’s connection string utility, then save the connection string for later use.

5. Create a .prp file (for example microsoft-teams.prp) with the JDBC connection details. Include the prefix, server name, server version, driver path, driver class, and the JDBC URL.

6. Run the MCP server using the stdio command. This starts the server and loads your JDBC connection from the .prp file.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/microsoft-teams.prp

Additional setup notes

The server runs locally and exposes data via the MCP interface. Ensure your Claude Desktop or other MCP client is configured to discover and start the server entry as described in the client’s MCP configuration flow.

Available tools

msteams_get_tables

Retrieves a list of tables available in the data source. Output is in CSV format with headers.

msteams_get_columns

Retrieves a list of columns for a specified table. Output is in CSV format with headers.

msteams_run_query

Executes a SQL SELECT query against the connected data source.