Skip to main content
Glama

GigAPI MCP Server

by gigapi
GitHub
Python
5
OverviewInspectNewSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

GigAPI MCP Server

An MCP server for GigAPI Timeseries Lake that provides seamless integration with Claude Desktop and other MCP-compatible clients.

Features

GigAPI Tools

  • run_select_query
    • Execute SQL queries on your GigAPI cluster.
    • Input: sql (string): The SQL query to execute, database (string): The database to execute against.
    • All queries are executed safely through GigAPI's HTTP API with NDJSON format.
  • list_databases
    • List all databases on your GigAPI cluster.
    • Input: database (string): The database to use for the SHOW DATABASES query (defaults to "mydb").
  • list_tables
    • List all tables in a database.
    • Input: database (string): The name of the database.
  • get_table_schema
    • Get schema information for a specific table.
    • Input: database (string): The name of the database, table (string): The name of the table.
  • write_data
    • Write data using InfluxDB Line Protocol format.
    • Input: database (string): The database to write to, data (string): Data in InfluxDB Line Protocol format.
  • health_check
    • Check the health status of the GigAPI server.
  • ping
    • Ping the GigAPI server to check connectivity.

Quick Start

1. Install the MCP Server

# The package will be available on PyPI after the first release # Users can install it directly with uv 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

2. Configure Claude Desktop

  1. Open the Claude Desktop configuration file located at:
    • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • On Windows: %APPDATA%/Claude/claude_desktop_config.json
  2. Add the following configuration:
{ "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" } } } }
For Local Development
{ "mcpServers": { "mcp-gigapi": { "command": "uv", "args": [ "run", "--with", "mcp-gigapi", "--python", "3.13", "mcp-gigapi" ], "env": { "GIGAPI_HOST": "localhost", "GIGAPI_PORT": "7971", "GIGAPI_TIMEOUT": "30", "GIGAPI_VERIFY_SSL": "false", "GIGAPI_DEFAULT_DATABASE": "mydb" } } } }
With Authentication
{ "mcpServers": { "mcp-gigapi": { "command": "uv", "args": [ "run", "--with", "mcp-gigapi", "--python", "3.13", "mcp-gigapi" ], "env": { "GIGAPI_HOST": "your-gigapi-server", "GIGAPI_PORT": "7971", "GIGAPI_USERNAME": "your_username", "GIGAPI_PASSWORD": "your_password", "GIGAPI_TIMEOUT": "30", "GIGAPI_VERIFY_SSL": "true", "GIGAPI_DEFAULT_DATABASE": "your_database" } } } }
  1. Important: Replace the uv command with the absolute path to your uv executable:
    which uv # Find the path
  2. Restart Claude Desktop to apply the changes.

API Compatibility

This MCP server is designed to work with GigAPI's HTTP API endpoints:

Query Endpoints

  • POST /query?db={database}&format=ndjson - Execute SQL queries with NDJSON response format
  • All queries return NDJSON (Newline Delimited JSON) format for efficient streaming

Write Endpoints

  • POST /write?db={database} - Write data using InfluxDB Line Protocol

Administrative Endpoints

  • GET /health - Health check
  • GET /ping - Simple ping

Example Usage

Writing Data

Use InfluxDB Line Protocol format:

curl -X POST "http://localhost:7971/write?db=mydb" --data-binary @/dev/stdin << EOF weather,location=us-midwest,season=summer temperature=82 weather,location=us-east,season=summer temperature=80 weather,location=us-west,season=summer temperature=99 EOF

Reading Data

Execute SQL queries via JSON POST with NDJSON format:

curl -X POST "http://localhost:7971/query?db=mydb&format=ndjson" \ -H "Content-Type: application/json" \ -d '{"query": "SELECT time, temperature FROM weather WHERE time >= epoch_ns('\''2025-04-24T00:00:00'\''::TIMESTAMP)"}'

Show Databases/Tables

# Show databases curl -X POST "http://localhost:7971/query?db=mydb&format=ndjson" \ -H "Content-Type: application/json" \ -d '{"query": "SHOW DATABASES"}' # Show tables curl -X POST "http://localhost:7971/query?db=mydb&format=ndjson" \ -H "Content-Type: application/json" \ -d '{"query": "SHOW TABLES"}' # Count records curl -X POST "http://localhost:7971/query?db=mydb&format=ndjson" \ -H "Content-Type: application/json" \ -d '{"query": "SELECT count(*), avg(temperature) FROM weather"}'

Environment Variables

Required Variables

  • GIGAPI_HOST: The hostname of your GigAPI server
  • GIGAPI_PORT: The port number of your GigAPI server (default: 7971)

Optional Variables

  • GIGAPI_USERNAME or GIGAPI_USER: The username for authentication (if required)
  • GIGAPI_PASSWORD or GIGAPI_PASS: The password for authentication (if required)
  • GIGAPI_TIMEOUT: Request timeout in seconds (default: 30)
  • GIGAPI_VERIFY_SSL: Enable/disable SSL certificate verification (default: true)
  • GIGAPI_DEFAULT_DATABASE: Default database to use for queries (default: mydb)
  • GIGAPI_MCP_SERVER_TRANSPORT: Sets the transport method for the MCP server (default: stdio)
  • GIGAPI_ENABLED: Enable/disable GigAPI functionality (default: true)

Example Configurations

For Local Development
# Required variables GIGAPI_HOST=localhost GIGAPI_PORT=7971 # Optional: Override defaults for local development GIGAPI_VERIFY_SSL=false GIGAPI_TIMEOUT=60 GIGAPI_DEFAULT_DATABASE=mydb
For Production with Authentication
# Required variables GIGAPI_HOST=your-gigapi-server GIGAPI_PORT=7971 GIGAPI_USERNAME=your_username GIGAPI_PASSWORD=your_password # Optional: Production settings GIGAPI_VERIFY_SSL=true GIGAPI_TIMEOUT=30 GIGAPI_DEFAULT_DATABASE=your_database
For Public Demo
GIGAPI_HOST=gigapi.fly.dev GIGAPI_PORT=443 GIGAPI_VERIFY_SSL=true GIGAPI_DEFAULT_DATABASE=mydb

Data Format

GigAPI uses Hive partitioning with the structure:

/data /mydb /weather /date=2025-04-10 /hour=14 *.parquet metadata.json

Development

Setup Development Environment

  1. Install dependencies:
    uv sync --all-extras --dev source .venv/bin/activate
  2. Create a .env file in the root of the repository:
    GIGAPI_HOST=localhost GIGAPI_PORT=7971 GIGAPI_USERNAME=your_username GIGAPI_PASSWORD=your_password GIGAPI_TIMEOUT=30 GIGAPI_VERIFY_SSL=false GIGAPI_DEFAULT_DATABASE=mydb
  3. For testing with the MCP Inspector:
    fastmcp dev mcp_gigapi/mcp_server.py

Running Tests

# Run all tests uv run pytest -v # Run only unit tests uv run pytest -v -m "not integration" # Run only integration tests uv run pytest -v -m "integration" # Run linting uv run ruff check . # Test with public demo python test_demo.py

Testing with Public Demo

The repository includes a test script that validates the MCP server against the public GigAPI demo:

python test_demo.py

This will test:

  • ✅ Health check and connectivity
  • ✅ Database listing (SHOW DATABASES)
  • ✅ Table listing (SHOW TABLES)
  • ✅ Data queries (SELECT count(*) FROM table)
  • ✅ Sample data retrieval

PyPI Publishing

This package is automatically published to PyPI on each GitHub release. The publishing process is handled by GitHub Actions workflows:

  • CI Workflow (.github/workflows/ci.yml): Runs tests on pull requests and pushes to main
  • Publish Workflow (.github/workflows/publish.yml): Publishes to PyPI when a release is created

For Users

Once published, users can install the package directly from PyPI:

# Install and run the MCP server uv run --with mcp-gigapi --python 3.11 mcp-gigapi

For Maintainers

To publish a new version:

  1. Update the version in pyproject.toml
  2. Create a GitHub release
  3. The workflow will automatically publish to PyPI

See RELEASING.md for detailed release instructions.

Troubleshooting

Common Issues

  1. Connection refused: Check that GigAPI is running and the host/port are correct
  2. Authentication failed: Verify username/password are correct
  3. SSL certificate errors: Set GIGAPI_VERIFY_SSL=false for self-signed certificates
  4. No databases found: Ensure you're using the correct default database (usually "mydb")

Debug Mode

Enable debug logging by setting the log level:

import logging logging.basicConfig(level=logging.DEBUG)

License

Apache-2.0 license

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Add tests
  5. Submit a pull request

Support

Install Server
A
security – no known vulnerabilities
F
license - not found
A
quality - confirmed to work

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

Tools

An MCP server that provides seamless integration with Claude Desktop for querying and managing timeseries data in GigAPI Timeseries Lake.

  1. Features
    1. GigAPI Tools
  2. Quick Start
    1. 1. Install the MCP Server
    2. 2. Configure Claude Desktop
  3. API Compatibility
    1. Query Endpoints
    2. Write Endpoints
    3. Administrative Endpoints
  4. Example Usage
    1. Writing Data
    2. Reading Data
    3. Show Databases/Tables
  5. Environment Variables
    1. Required Variables
    2. Optional Variables
    3. Example Configurations
  6. Data Format
    1. Development
      1. Setup Development Environment
      2. Running Tests
      3. Testing with Public Demo
    2. PyPI Publishing
      1. For Users
      2. For Maintainers
    3. Troubleshooting
      1. Common Issues
      2. Debug Mode
    4. License
      1. Contributing
        1. Support

          Related MCP Servers

          • ticktick-mcp-server

            jacepark12
            -
            security
            F
            license
            -
            quality
            A MCP server for TickTick that enables interacting with your TickTick task management system directly through Claude and other MCP clients.
            Last updated -
            104
            Python
            • Apple

          • FreeAgent MCP Server

            markpitt
            A
            security
            A
            license
            A
            quality
            A Claude MCP server that allows Claude to interact with your FreeAgent account to track time, manage timers, and handle timeslip operations.
            Last updated -
            7
            1
            JavaScript
            MIT License
            • Linux
            • Apple

          • Ledger MCP Server

            mprokopov
            -
            security
            A
            license
            -
            quality
            An MCP server that allows accessing and managing ledger files through Claude by providing account listing, balance checking, and transaction register viewing capabilities.
            Last updated -
            3
            Python
            GPL 3.0
            • Apple

          • Choose MCP Server

            keurcien
            -
            security
            F
            license
            -
            quality
            An MCP server for Claude Desktop that allows users to query data from selected Google Cloud datasets by configuring project ID and datasets in the Claude Desktop configuration.
            Last updated -
            Python
            • Apple

          View all related MCP servers

          New MCP Servers

          MCP directory API

          We provide all the information about MCP servers via our MCP API.

          curl -X GET 'https://glama.ai/api/mcp/v1/servers/gigapi/gigapi-mcp'

          If you have feedback or need assistance with the MCP directory API, please join our Discord server