home / mcp / apache couchdb mcp server

Apache CouchDB MCP Server

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

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can run a read-only MCP server that exposes live Apache CouchDB data through a simple MCP interface. This enables large language models to query your CouchDB data directly, without writing SQL, while keeping data access lightweight and queryable in real time.

How to use

After you have the MCP server running, you use an MCP-enabled client to interact with the CouchDB data. You do not need to call individual tools explicitly for common queries; simply ask the client questions about the underlying data. For example, you can ask about correlations between opportunities and account attributes, counts of open items in a project, or upcoming calendar events, and the MCP server will translate those requests into read-only data queries under the hood.

How to install

# Prerequisites
- Java (JRE/JDK) installed and available on your system
- Maven or your preferred build tool available on the PATH

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

# 2. Build the server
mvn clean install

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

# 3. Install the CData JDBC Driver for CouchDB (download from CData)
# 4. License the CData JDBC Driver (example on Windows/Linux/macOS):
#    java -jar cdata.jdbc.couchdb.jar --license
#    Enter your name, email, and license key when prompted

# 5. Configure your JDBC connection (example path shown; adapt as needed)
# Run the Connection String utility to generate a JDBC URL and test it
java -jar cdata.jdbc.couchdb.jar

# 6. Create a .prp file for the JDBC connection (example content shown):
#    Prefix=couchdb
#    ServerName=CDataCouchDB
#    ServerVersion=1.0
#    DriverPath=PATH\TO\cdata.jdbc.couchdb.jar
#    DriverClass=cdata.jdbc.couchdb.CouchDBDriver
#    JdbcUrl=jdbc:couchdb:InitiateOAuth=GETANDREFRESH;
#    Tables=

# 7. Run the MCP server using the provided PRP (example uses Salesforce.prp as a placeholder in this setup)
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp

Additional configuration and notes

Configure the MCP server for Claude Desktop or another MCP client by creating or updating the client config to include the MCP server entry. The example configuration shows how to point the MCP client to the Java-based MCP server executable and supply the PRP path. Make sure the path values reflect your environment.

If you need to run the server on a specific machine, ensure the Java process has the necessary permissions and that the path to the PRP file and the JAR file is accessible. For best results, keep the server on a machine with reliable network access if you plan to query live data from other tools or clients.

Troubleshooting

If the MCP server does not appear in your MCP client, fully quit and restart the client to refresh the server list. Verify that the JDBC connection string is correct and tested successfully before starting the MCP server. If you encounter connection issues, confirm that the data source is reachable and that the JDBC driver is licensed correctly. If problems persist, contact CData Support or join the CData Community for guidance.

Licensing and compliance

This MCP server is distributed under the MIT License. You are free to use, modify, and distribute the software in compliance with the MIT terms.

Available tools

apache_couchdb_get_tables

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

apache_couchdb_get_columns

Retrieves a list of columns for a specified table. Output is CSV with column headers in the first line.

apache_couchdb_run_query

Executes a SQL SELECT query against the data source and returns the result set.