- Home
- MCP servers
- Odoo
Odoo
- other
1
GitHub Stars
other
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"cdatasoftware-odoo-mcp-server-by-cdata": {
"command": "java",
"args": [
"-jar",
"PATH\\\\TO\\\\CDataMCP-jar-with-dependencies.jar",
"PATH\\\\TO\\\\odoo.prp"
]
}
}
}You can run a local, read-only MCP server that exposes live Odoo data through a simple MCP interface. This enables LLMs to query Odoo data using natural language without writing SQL, while keeping data access secure and read-only.
How to use
Once your MCP server is running, you connect an MCP client (such as Claude Desktop) to the local server to ask questions about live Odoo data. You don’t need to write SQL queries; just ask questions like “What is the total value of open opportunities by customer industry?” or “Show me the latest invoices for last month.” The server handles data retrieval behind the scenes and returns results in a structured format that the AI client can understand.
How to install
Prerequisites you need before starting: a Java runtime environment and Maven for building the server.
# 1) Clone the MCP server repository
git clone https://github.com/cdatasoftware/odoo-mcp-server-by-cdata.git
cd odoo-mcp-server-by-cdata
# 2) Build the server to produce the JAR
mvn clean install
# 3) Download and install the CData JDBC Driver for Odoo
# URL: https://www.cdata.com/drivers/odoo/download/jdbc
# 4) License the CData JDBC Driver (run from the driver's lib folder)
java -jar cdata.jdbc.odoo.jar --license
# Enter your name, email, and license type as prompted
# 5) Configure your connection to the data source (example shown for Salesforce, adjust as needed)
java -jar cdata.jdbc.odoo.jar
# Use the Connection String utility, Test Connection, and copy the resulting JDBC URL for later use
# 6) Create a .prp file for the JDBC connection (odoo.prp)
# Example contents (adjust paths accordingly)
Additional sections
Server configuration and usage details are below. Follow these steps to run the MCP server locally and expose Odoo data to your MCP client.
Run the MCP server on its own using the final start command shown here. The server runs via stdio and is intended for clients on the same machine.
Configuration and runtime notes
The Odoo MCP server is started with a standard Java command that loads a prepared property file (odoo.prp). Ensure the path to the JAR and the path to odoo.prp are correct for your environment.
Available tools
odoo_get_tables
Retrieves a list of tables available in the data source. The output is in CSV format, with column headers on the first line.
odoo_get_columns
Retrieves a list of columns for a specified table. The output is in CSV format, with column headers on the first line.
odoo_run_query
Executes a SQL SELECT query against the Odoo data exposed by the MCP server and returns the results.