Skip to main content
Glama
TonyC793

SAMS Catalog MCP Server

by TonyC793
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

SAMS Catalog MCP Server

MCP server for catalog management service for the SAMS platform with ADK integration support.

Quick Start

Standalone Operation

  1. Install Dependencies

    pip install uv
uv sync

  2. Configure the Server Create or modify config/config.json with your API configurations:

    {
  "api_connections": {
    "iqs": {
       "base_url"
      "timeout": 30,
      "max_retries": 3,
      "ssl_verify": false
    }
  },
  "server": {
    "host": "0.0.0.0",
    "port": 8080,
    "debug": true
  }
}

  3. Run the Server

    # Simple command using uv
uv run python main.py

# Or using the script entry point (if defined in pyproject.toml)
uv run mcp-server

Configuration via JSON

The server reads its configuration from a config.json file. The config file can be located in:

  1. Path specified by CONFIG_JSON_PATH environment variable

  2. /etc/secrets/config.json (for Docker/Kubernetes deployments)

  3. config/config.json (relative to the project root)

  4. config.json (current working directory)

Configuration Structure:

{
  "api_connections": {
    "iqs": {
      "base_url"
      "timeout": 30,
      "max_retries": 3,
      "ssl_verify": false
    },
    "iro": { ... },
    "elixir_v1": { ... },
    "elixir_v2": { ... },
    "score_v1": { ... },
    "mapper": { ... }
  },
  "server": {
    "host": "0.0.0.0",
    "port": 8080,
    "debug": true
  },
  "analysis": {
    "false_positive_threshold": 0.95,
    "merge_confidence_threshold": 0.8
  },
  "log_level": "INFO"
}

Environment Variables (Optional):

# Configuration Override
CONFIG_JSON_PATH=/path/to/your/config.json  # Override config file location

# Server Override (will override JSON values if set)
SERVER_PORT=8080          # Server port
DEBUG=true               # Debug mode
LOG_LEVEL=INFO          # Logging level

Development

# Run in development mode
DEBUG=true LOG_LEVEL=DEBUG uv run python main.py

# Run on different port
SERVER_PORT=9000 uv run python main.py

# Use custom config file
CONFIG_JSON_PATH=/path/to/custom/config.json uv run python main.py

Docker

### Docker

```bash
# Build and run with docker-compose (uses config/config.json)
docker-compose up --build

# Or direct docker run with custom config
docker run -v /path/to/your/config.json:/etc/secrets/config.json:ro -p 8080:8080 sams-catalog-mcp

docker build -t sams-catalog-mcp . docker run -p 8080:8080 --env-file .env sams-catalog-mcp


### Testing

```bash
# Test server health
curl http://localhost:8080/health

# Test MCP protocol
curl -X POST http://localhost:8080/mcp \
  -H "Content-Type: application/json" \
  -d '{"method": "tools/list"}'

# List available tools
curl http://localhost:8080/tools

Related MCP server: AXT-MCP

ADK Integration

The server now works seamlessly with ADK without command-line arguments:

{
  "mcpServers": {
    "sams-catalog-mcp": {
      "command": "uv",
      "args": ["run", "python", "main.py"],
      "transport": "streamable-http",
      "endpoint": "http://localhost:8080/mcp",
      "env": {
        "PYTHONPATH": "/path/to/sams-catalog-mcp",
        "PYTHONUNBUFFERED": "1",
        "SERVER_PORT": "8080"
      }
    }
  }
}

This server cannot be deployed

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Kroger MCP Server

    EricLott
    A
    license
    Not graded
    quality
    D
    maintenance
    Allows Large Language Models to interact with Kroger's grocery services, enabling product search, store lookup, and cart management through the Model Context Protocol.
    3
    MIT

  • AXT-MCP

    codyterry24-dev
    -
    license
    Not graded
    quality
    Not graded
    maintenance
    A Model Context Protocol service registry and connector framework that enables seamless integration with multiple services and models through a standardized API interface. Provides an extensible architecture for custom service adapters, API integrations, and model registries.
    -

  • Azure APIM + MCP Server Demo

    kathirt
    A
    license
    Not graded
    quality
    D
    maintenance
    Exposes backend APIs through Azure API Management as an MCP server to enable AI assistants to interact with product catalogs and order systems. It provides standardized tools for searching products, retrieving details, and managing orders via the Model Context Protocol.
    MIT