home / mcp / gigapi mcp server

GigAPI MCP Server

MCP Service for GigAPI Timeseries Lake

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "gigapi-gigapi-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp-gigapi",
        "--python",
        "3.13",
        "mcp-gigapi"
      ],
      "env": {
        "GIGAPI_HOST": "gigapi.fly.dev",
        "GIGAPI_PORT": "443",
        "GIGAPI_TIMEOUT": "30",
        "GIGAPI_PASSWORD": "your_password",
        "GIGAPI_USERNAME": "your_username",
        "GIGAPI_VERIFY_SSL": "true",
        "GIGAPI_DEFAULT_DATABASE": "mydb"
      }
    }
  }
}

You run a GigAPI MCP Server to expose your GigAPI Timeseries Lake data to MCP-compatible clients, enabling SQL-like queries, data writes, health checks, and convenient integration with tools like Claude Desktop. This guide shows you how to install, configure, and use the server so you can query, write, and manage data from MCP clients.

How to use

You interact with the GigAPI MCP Server through an MCP client. The server exposes endpoints for running SQL-like queries against GigAPI, writing data with InfluxDB Line Protocol, and performing health checks. Common usage patterns include querying for time-series data, listing databases and tables, and writing new measurements.

To connect your MCP client, configure the MCP integration so it knows where GigAPI is and which database to use by default. If you are using the public demo, you will point the client to the demo host and port and set the default database accordingly.

Example tasks you can perform once connected include: - Run read queries to retrieve temperature or other metrics over a time range. - Write new measurements using InfluxDB Line Protocol to your chosen database. - Check the health of the GigAPI endpoint to ensure the MCP connection stays reliable.

How to install

Prerequisites you need before installing: - Python environment available (for the MCP server runtime). - The MCP runtime command line tool you use to run MCP servers (commonly uv). - Network access to GigAPI or the public demo endpoint if you are testing.

# Option A: From PyPI (Recommended)
# Install the MCP server package and start it with the MCP runtime
uv run --with mcp-gigapi --python 3.11 mcp-gigapi --help

# Option B: From Source
# Clone the repository
git clone https://github.com/gigapi/mcp-gigapi.git
cd mcp-gigapi

# Install dependencies
uv sync

Configuration and usage notes

Configuration is typically done through the MCP client or the environment you run the MCP server in. The server relies on GigAPI host/port settings and optional authentication. For testing with a public demo, you can configure the MCP client to point to the demo host and port and set default database as shown in the example configuration.

Public demo configuration (for testing): the MCP server is run with the following environment and command composition to connect to the public GigAPI endpoint.

{
  "mcpServers": {
    "mcp-gigapi": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp-gigapi",
        "--python",
        "3.13",
        "mcp-gigapi"
      ],
      "env": {
        "GIGAPI_HOST": "gigapi.fly.dev",
        "GIGAPI_PORT": "443",
        "GIGAPI_TIMEOUT": "30",
        "GIGAPI_VERIFY_SSL": "true",
        "GIGAPI_DEFAULT_DATABASE": "mydb"
      }
    }
  }
}

Security and access notes

If your GigAPI server requires authentication, provide a username and password in the environment where you run the MCP server. Ensure that SSL verification is enabled for production environments to protect credentials in transit.

Available tools

run_select_query

Execute SQL queries against GigAPI via the MCP server and return results in NDJSON format.

list_databases

List all databases on your GigAPI cluster.

list_tables

List all tables in a specified database.

get_table_schema

Retrieve schema information for a specific table.

write_data

Write data using InfluxDB Line Protocol to a specified database.

health_check

Check the health status of the GigAPI server.

ping

Ping the GigAPI server to verify connectivity.