home / mcp / instagram mcp server

Instagram MCP Server

This read-only MCP Server allows you to connect to Instagram 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-instagram-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/instagram.prp"
      ]
    }
  }
}

You can run a local MCP server that exposes live Instagram data via a JDBC-backed model, enabling language models to query data without writing SQL. This server is read-only by default and is designed for easy, on‑device access to Instagram data through the MCP interface.

How to use

Once the MCP server is running, you interact with it through an MCP client. You do not need to write SQL queries; instead, you ask natural language questions about Instagram data and the client routes those requests to the server. Useful patterns include asking for counts, latest items, or summaries across profiles, posts, or comments, and combining data points to inform decision making.

How to install

Prerequisites: Java runtime and Maven are required to build and run the server.

git clone https://github.com/cdatasoftware/instagram-mcp-server-by-cdata.git
cd instagram-mcp-server-by-cdata
mvn clean install

This build creates the MCP server JAR named CDataMCP-jar-with-dependencies.jar.

Next, you prepare the data source connection using the CData JDBC Driver for Instagram. You will download, license, and configure the driver, and then create a properties file for the MCP server to point to your data source.

Key steps include: - Download and install the CData JDBC Driver for Instagram - License the driver with your details - Run the driver connection utility to obtain a JDBC URL - Create a .prp file with your JDBC configuration (Prefix, ServerName, ServerVersion, DriverPath, DriverClass, JdbcUrl, Tables)

Running the server

To start the MCP server locally, run the following command using your built JAR and the prepared .prp file. This uses stdio so the server runs on the same machine as the client.

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

Using Claude Desktop or another MCP client

Configure your MCP client to load the local server. The typical setup is to point the client to the locally running MCP process and reference the instagram.prp file. You may need to restart the client after adding the MCP configuration so the new server appears in your list of available MCP servers.

Tools and capabilities

The server exposes a small set of MCP tools to interact with the underlying data model. You can list available tables, list columns for a table, and run a query against the data source.

Security and best practices

Operate the MCP server on a trusted machine. If you enable network access, secure the host and limit exposure to trusted clients. Use strong access controls around the client that consumes the MCP data, and rotate any credentials used for the JDBC connection string regularly.

Troubleshooting

If the MCP server does not appear in your client, ensure you have fully quit and restarted the client after adding the server configuration. Confirm the Java command and the paths in your instagram.prp file are correct. If you encounter connectivity or data access problems, validate the JDBC connection string and test the connection via the CData JDBC Driver utilities.

License

This MCP server is available under the MIT License. You may use, modify, and distribute it in compliance with the license terms.

Notes

This is a local, read-only MCP server intended for live Instagram data access through the CData JDBC Driver. For fully remote MCP access with write capabilities, explore other MCP platforms offered by the provider.

Available tools

instagram_get_tables

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

instagram_get_columns

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

instagram_run_query

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