home / mcp / pipedrive mcp server

Pipedrive MCP Server

This read-only MCP Server allows you to connect to Pipedrive data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for Pipedrive (https://www.cdata.com/drivers/pipedrive/download/mcp).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

Pipedrive MCP Server by CData provides a read-only MCP interface that exposes live Pipedrive data through the CData JDBC Driver, enabling language models and clients to query data without writing SQL.

How to use

Once the MCP server is running, you can interact with it from an MCP client (such as Claude Desktop) or any client that supports the MCP protocol. You’ll issue read-oriented queries to retrieve live Pipedrive data, such as opportunities, accounts, and activities, without composing SQL. Use natural language prompts or the client’s tool-assisted queries to list available tables, inspect columns, and run read queries against your Pipedrive data through the MCP server. The server is designed to be lightweight and read-only, making it straightforward to probe data and answer questions like which opportunities are open by account, which activities are scheduled today, or how revenue correlates with deal stage.

How to install

Prerequisites: You need a Java runtime and Maven to build and run the MCP server. You also need the CData JDBC Driver for Pipedrive (download separately) to provide the underlying data connectivity.

# 1. Clone the repository
git clone https://github.com/cdatasoftware/pipedrive-mcp-server-by-cdata.git
cd pipedrive-mcp-server-by-cdata

# 2. Build the server
mvn clean install

# This creates the JAR file: CDataMCP-jar-with-dependencies.jar

3. Download and install the CData JDBC Driver for Pipedrive from the vendor site. 4. License the CData JDBC Driver using the driver’s license command and place the license in the appropriate location. 5. Configure your connection to the data source using the Connection String utility, then copy the connection string for later use in a .prp file. 6. Create a .prp file (e.g., pipedrive.prp) with the required properties to define your MCP server, including the JDBC driver path, connection string, and target tables.

Prefix=pipedrive
ServerName=CDataPipedrive
ServerVersion=1.0
DriverPath=PATH\\TO\\cdata.jdbc.pipedrive.jar
DriverClass=cdata.jdbc.pipedrive.PipedriveDriver
JdbcUrl=jdbc:pipedrive:InitiateOAuth=GETANDREFRESH;
Tables=

Additional setup details

Using Claude Desktop or another MCP client, you will create a config that tells the client how to launch the MCP server. The README provides Windows and Linux/macOS examples for wiring together the Java runtime, the MCP JAR, and the .prp connection file. The server runs as a local process and communicates via stdio, so the client and server must run on the same machine.

{
  "mcpServers": {
    "pipedrive": {
      "command": "PATH\\TO\\java.exe",
      "args": [
        "-jar",
        "PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
        "PATH\\TO\\pipedrive.prp"
      ]
    }
  }
}

Running the server

Start the MCP server with the Java runtime and the prepared .prp file. The server will listen for commands from the MCP client on the local machine.

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

Notes on usage and examples

The MCP server provides read-only access to Pipedrive data via the standard MCP tools exposed by the server. You can query for tabular metadata, perform read queries, and fetch results in a structured format suitable for downstream processing by language models and agents.