home / mcp / avro mcp server

Avro MCP Server

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

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can run a read-only MCP server that exposes live Avro data through a simple MCP interface, letting you ask questions in natural language and retrieve up-to-date results without writing SQL. This server wraps the CData JDBC Driver for Avro and makes Avro data accessible to compatible MCP clients.

How to use

Once the MCP server is running, your MCP client can discover and query live Avro data through the built-in tools. You interact by asking questions or issuing simple queries that the client translates into MCP tool calls under the hood. Typical use cases include listing available tables, inspecting columns, and running read-only SELECT-like queries to retrieve data.

How to install

Prerequisites: Java Runtime Environment (JRE) and Maven are required to build and run the MCP server. You will also need the CData JDBC Driver for Avro installed on the system where you run the server.

Step-by-step installation and run

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

# 2. Build the server
mvn clean install
# This creates the JAR: CDataMCP-jar-with-dependencies.jar

# 3. Download and install the CData JDBC Driver for Avro
# Visit: https://www.cdata.com/drivers/avro/download/jdbc

# 4. License the CData JDBC Driver
# Open a terminal in the lib folder of the driver installation and run:
java -jar cdata.jdbc.avro.jar --license
# Enter your name, email, and TRIAL (or your license key).

# 5. Configure your connection to the data source (example uses Salesforce)
# Open the Connection String utility:
java -jar cdata.jdbc.avro.jar
# Configure connection string, then Test Connection. Copy the resulting string.

# 6. Create a .prp file for the JDBC connection (e.g., avro.prp)

Start the MCP server

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/avro.prp
```
> Note: The server Uses stdio and runs on the same machine as the client.

Available tools

avro_get_tables

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

avro_get_columns

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

avro_run_query

Executes a SQL SELECT query against the Avro data source and returns results.