test-dh-mcp

@chipkent

About test-dh-mcp

Explore creating a Deephaven Core MCP server

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "test-dh-mcp": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "<package>"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is test-dh-mcp?

test-dh-mcp is a demonstration MCP (Model Context Protocol) server built with FastMCP, integrating Deephaven data workers. It provides tools for querying and managing Deephaven tables and is intended for developers using MCP clients like Claude Desktop.

How to use test-dh-mcp?

Install dependencies with pip or uv, then run the server with python src/mcp_server.py using either SSE (default, on port 8000) or stdio transport. The server connects to Deephaven workers defined in a JSON config file specified by the DH_MCP_CONFIG_FILE environment variable. Clients must use SSE transport; Claude Desktop configuration requires stdio transport.

Key features of test-dh-mcp

Supports SSE and stdio transport modes.
Integration with Deephaven data workers.
Configurable multiple Deephaven workers via JSON file.
Includes example client (mcp_client.py) for testing.
Designed for use with Claude Desktop and MCP Inspector.
Tools for listing tables and schemas from Deephaven.

Use cases of test-dh-mcp

Querying table names and schemas from a Deephaven instance via MCP.
Building custom MCP clients that interact with Deephaven data.
Testing and debugging MCP tools with MCP Inspector.
Integrating Deephaven data into Claude Desktop workflows.
Demonstrating FastMCP server development with real data backends.

FAQ from test-dh-mcp

What is the DH_MCP_CONFIG_FILE environment variable?

It is a required environment variable that specifies the path to a JSON config file defining Deephaven workers. There is no default path; it must be set.

What tools does test-dh-mcp provide?

Tools include echo_tool, gnome_count_colorado, deephaven_worker_names, deephaven_default_worker, deephaven_list_tables, and deephaven_table_schemas.

Does the client work with stdio mode?

No, the Python client (mcp_client.py) only works when the server is running in SSE mode. Stdio mode is intended for Claude Desktop and MCP Inspector integration.

How do I configure Deephaven workers?

Create a JSON config file with a workers object mapping names to connection settings (host, port, auth_type, etc.) and optionally a default_worker. Specify the file path via DH_MCP_CONFIG_FILE.

How can I test the server with MCP Inspector?

Install the MCP Inspector via npm, then run it with the server command, passing the appropriate Python or uv executable and ensuring to use quoted string values for parameters.

Frequently asked questions

What is the DH_MCP_CONFIG_FILE environment variable?

It is a required environment variable that specifies the path to a JSON config file defining Deephaven workers. There is no default path; it must be set.

What tools does test-dh-mcp provide?

Tools include echo_tool, gnome_count_colorado, deephaven_worker_names, deephaven_default_worker, deephaven_list_tables, and deephaven_table_schemas.

Does the client work with stdio mode?

No, the Python client (`mcp_client.py`) only works when the server is running in SSE mode. Stdio mode is intended for Claude Desktop and MCP Inspector integration.

How do I configure Deephaven workers?

Create a JSON config file with a workers object mapping names to connection settings (host, port, auth_type, etc.) and optionally a default_worker. Specify the file path via DH_MCP_CONFIG_FILE.

How can I test the server with MCP Inspector?

Install the MCP Inspector via npm, then run it with the server command, passing the appropriate Python or uv executable and ensuring to use quoted string values for parameters.

Comments

Basic information

More Developer Tools MCP servers

BetterBugs

The BetterBugs MCP (Model Context Protocol) enables you to load BetterBugs bug reports (via report links) directly to your preferred AI Agents and developer environments with MCP Client capabilities (such as Cursor, VS C