home / mcp / slack mcp server

Slack MCP Server

Provides a read-only MCP server exposing Slack data via the CData JDBC Driver for use with LLMs.

Installation

Add the following to your MCP client configuration file.

Configuration

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

You can run a local, read-only MCP server that exposes live Slack data via a simple MCP interface. This lets your AI tools ask natural language questions and retrieve up‑to‑date Slack information without writing SQL. The server reads data through the CData JDBC Driver for Slack and presents it as MCP tools you can call from your client.

How to use

You will connect your MCP client to the local server that runs on your machine. Start the server with a local command, then use your MCP client to call the exposed tools. You don’t need to write SQL; simply ask questions like “What are open Slack channels this week?” or call tools to fetch table lists, columns, or run a query. The server operates on stdio, so it communicates with clients running on the same machine.

Once the server starts, your MCP client can use the built‑in tools to discover data and retrieve results in your preferred format (CSV for tabular data, etc.). Examples of typical tool names include the table and column explorers and a query tool that runs a SELECT against Slack data. You generally don’t call the tools directly; just ask your client to retrieve the information you need and the MCP layer will execute the underlying queries.

How to install

Prerequisites you need before starting: Java Runtime Environment (JRE) or JDK, and Maven for building the MCP server. Have a Slack data source configured via the CData JDBC Driver for Slack. You will also need a Slack connection string generated through the CData JDBC Driver tooling.

1) Clone the MCP server repository.

2) Build the server package.

3) Install the CData JDBC Driver for Slack and license it using the driver’s license utility.

4) Configure the JDBC connection to Slack and obtain the connection string. If you use OAuth, complete the authentication in your browser and copy the resulting connection string.

5) Create the Slack MCP configuration file Slack.prp with your JDBC details, including the driver path, driver class, and connection string. Leave Tables blank to access all data or specify specific tables.

6) Run the MCP server using the stdio command below. The server will listen on the local machine and be accessible to your MCP client.

Configuration and run details

Prepare a Slack.prp file with the following properties (adjust paths to your environment):

Prefix=slack
ServerName=CDataSlack
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.slack.jar
DriverClass=cdata.jdbc.slack.SlackDriver
JdbcUrl=jdbc:slack:InitiateOAuth=GETANDREFRESH;
Tables=

Running the server

Start the MCP server on the same machine as your client using the following command. Replace the PATH placeholders with your actual file locations.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/slack.prp

Available tools

slack_get_tables

Retrieves the list of Slack data tables available through the MCP server and outputs the results in CSV format with the first line as column headers.

slack_get_columns

Retrieves the list of columns for a specified Slack data table and returns results in CSV format with headers.

slack_run_query

Executes a SQL SELECT query against the Slack data exposed by the MCP server to return matching results.