MCP Openhexa

Provides a local MCP server to access OpenHEXA data sources and actions through Claude Desktop.
  • python

1

GitHub Stars

python

Language

5 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": {
    "mcrimi-mcp-openhexa": {
      "command": "{path}/mcp-openhexa/.venv/bin/python",
      "args": [
        "-m",
        "mcp_openhexa.server"
      ],
      "env": {
        "HEXA_TOKEN": "{YOUR TOKEN HERE}",
        "HEXA_SERVER_URL": "https://app.openhexa.org/"
      }
    }
  }
}

You run a local MCP server to connect Claude Desktop with OpenHEXA, enabling you to query workspaces, datasets, pipelines, and runs directly from your Claude conversations. This guide shows practical steps to install, configure, and start using the OpenHEXA MCP server with Claude Desktop.

How to use

After you have the OpenHEXA MCP server configured in Claude Desktop, you can ask Claude natural language questions to explore OpenHEXA data sources and actions. Examples include asking for workspaces, listing datasets in a workspace, searching pipelines by name, getting details about a dataset, and viewing recent runs of a pipeline. The MCP acts as a bridge between Claude Desktop and your OpenHEXA instance, running locally so your data stays within reach.

How to install

Prerequisites you need before starting:

npx -y @smithery/cli install @mcrimi/mcp-openhexa --client claude

Additional setup steps

Step 1. Set up a Python virtual environment and install dependencies.

pip install -r requirements.txt

Configure Claude Desktop

Step 2. Edit Claude Desktop’s configuration to include the OpenHEXA MCP server. Add or merge the following configuration into your Claude Desktop config file.

{
  "mcpServers": {
    "openhexa": {
      "command": "{path}/mcp-openhexa/.venv/bin/python",
      "args": ["-m", "mcp_openhexa.server"],
      "cwd": "{path}/mcp-openhexa",
      "env": {
        "HEXA_TOKEN": "{YOUR TOKEN HERE}",
        "HEXA_SERVER_URL": "https://app.openhexa.org/"
      }
    }
  }
}

Notes on configuration

Replace the placeholder values with your actual OpenHEXA token and server URL. After saving the configuration, restart Claude Desktop to enable the OpenHEXA integration.

Start using with Claude

Once configured, you can interact with OpenHEXA through Claude Desktop by asking questions like those shown here. You don’t need to know any JSON-RPC details; simply phrase your request as a natural question.

Troubleshooting tips

If Claude Desktop does not recognize OpenHEXA after restarting, verify that the Python virtual environment path in the command is correct for your system, ensure the token and server URL are valid, and confirm that your Claude configuration file was saved in the right location. Check that the MCP process starts without errors and that the OpenHEXA server is reachable at the configured URL.

Tools you can access with this MCP

OpenHEXA MCP exposes actions such as listing workspaces, listing datasets within a workspace, searching pipelines by name, fetching dataset details, and showing recent runs for a pipeline. These tools are exposed as natural language capabilities when you interact with Claude via the OpenHEXA MCP integration.

Security and best practices

Treat your OpenHEXA token as a secret. Do not share the token in public or unsafe channels. Use a dedicated token with least-privilege access for the MCP server integration, and rotate it periodically. Ensure that your local machine is secure and that the MCP server process runs with appropriate permissions.

Available tools

list_workspaces

Retrieves all workspaces available in your OpenHEXA account so you can choose where to operate.

list_datasets

Lists datasets within a specified workspace, enabling you to inspect available data assets.

search_pipelines

Searches pipelines by name or keyword to quickly locate processing workflows.

get_dataset_details

Shows detailed information about a specific dataset, including schema and metadata.

get_recent_runs

Shows recent runs for a given pipeline, helping you track activity and results.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational
MCP Openhexa MCP Server - mcrimi/mcp-openhexa | VeilStrat