Elasticsearch MCP server

This Python implementation of an MCP (Model Context Protocol) server integrates with Elasticsearch to provide a convenient interface for working with Claude AI models. The server bridges the gap between your applications and Claude models, utilizing Elasticsearch for data storage and retrieval.

Prerequisites

Before installation, ensure you have:

• Claude desktop application installed
• Elasticsearch instance running
• Python 3.10+ installed

Installation

1. Clone the repository

git clone https://github.com/anthropics/mcp.git
cd mcp

2. Configure environment variables

Create a .env file in the root directory with the following variables:

# Elasticsearch connection details
ELASTICSEARCH_URL=http://localhost:9200
ELASTICSEARCH_USERNAME=elastic
ELASTICSEARCH_PASSWORD=yourpassword

# Claude API configuration
CLAUDE_API_KEY=your_claude_api_key

# Server settings (optional)
PORT=8080
HOST=0.0.0.0

Adjust the values according to your specific setup.

3. Set up Claude configuration

Run the following command to add the Claude configuration:

make add-claude-config

4. Start the MCP server

Launch the server with:

make run

Usage

Connecting to the MCP server

Once the server is running, you can connect to it using standard HTTP requests. The default address is:

http://localhost:8080

Basic API endpoints

The MCP server exposes several endpoints for interacting with Claude models:

Creating a conversation

To create a new conversation:

curl -X POST http://localhost:8080/conversations \
  -H "Content-Type: application/json" \
  -d '{}'

Sending messages

To send a message to an existing conversation:

curl -X POST http://localhost:8080/conversations/{conversation_id}/messages \
  -H "Content-Type: application/json" \
  -d '{
    "role": "user",
    "content": "Hello, Claude!"
  }'

Retrieving conversation history

To fetch the conversation history:

curl -X GET http://localhost:8080/conversations/{conversation_id}/messages

Configuring search parameters

You can configure Elasticsearch search parameters when creating a conversation:

curl -X POST http://localhost:8080/conversations \
  -H "Content-Type: application/json" \
  -d '{
    "search_config": {
      "index": "my_documents",
      "fields": ["content", "title"],
      "max_results": 5
    }
  }'

Advanced Configuration

Customize Elasticsearch indexing

You can customize how documents are indexed and retrieved by modifying the search configuration:

curl -X POST http://localhost:8080/conversations \
  -H "Content-Type: application/json" \
  -d '{
    "search_config": {
      "index": "knowledge_base",
      "fields": ["text", "metadata"],
      "max_results": 10,
      "min_score": 0.75,
      "filters": [
        {"term": {"category": "technical"}}
      ]
    }
  }'

Working with multiple Claude models

Specify different Claude models when creating a conversation:

curl -X POST http://localhost:8080/conversations \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-opus-20240229"
  }'

Available models include:

• claude-3-opus-20240229
• claude-3-sonnet-20240229
• claude-3-haiku-20240307

Troubleshooting

Server connection issues

If you experience connection issues:

1. Verify Elasticsearch is running:

   curl http://localhost:9200
   

2. Check your .env configuration settings

3. Ensure Claude desktop is properly installed and configured

4. Examine the server logs for detailed error messages

API errors

Common HTTP status codes:

• 400: Bad request (invalid parameters)
• 404: Resource not found
• 500: Server error (check logs for details)

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "elasticsearch" '{"command":"python","args":["-m","mcp"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "elasticsearch": {
            "command": "python",
            "args": [
                "-m",
                "mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "elasticsearch": {
            "command": "python",
            "args": [
                "-m",
                "mcp"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect