This repository contains experimental features intended for research and evaluation and are not production-ready.
Connect to your Elasticsearch data directly from any MCP Client (like Claude Desktop) using the Model Context Protocol (MCP).
This server connects agents to your Elasticsearch data using the Model Context Protocol. It allows you to interact with your Elasticsearch indices through natural language conversations.
<a href="https://glama.ai/mcp/servers/@elastic/mcp-server-elasticsearch"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@elastic/mcp-server-elasticsearch/badge" alt="Elasticsearch Server MCP server" /> </a>https://github.com/user-attachments/assets/5dd292e1-a728-4ca7-8f01-1380d1bebe0c
Edit Config
and add a new MCP Server with the following configuration:{
"mcpServers": {
"elasticsearch-mcp-server": {
"command": "docker",
"args": [
"run", "--rm", "-i",
"-e", "ES_URL",
"-e", "ES_API_KEY",
"docker.elastic.co/mcp/elasticsearch", "stdio"
],
"env": {
"ES_URL": "<your-elasticsearch-url>",
"ES_API_KEY": "<your-api-key>"
}
}
}
}
Edit Config
and add a new MCP Server with the following configuration:{
"mcpServers": {
"elasticsearch-mcp-server": {
"command": "npx",
"args": [
"-y",
"@elastic/mcp-server-elasticsearch"
],
"env": {
"ES_URL": "<your-elasticsearch-url>",
"ES_API_KEY": "<your-api-key>",
"OTEL_LOG_LEVEL": "none"
}
}
}
}
The Elasticsearch MCP Server supports configuration options to connect to your Elasticsearch:
[!NOTE]
You must provide either an API key or both username and password for authentication.
Environment Variable | Description | Required |
---|---|---|
ES_URL | Your Elasticsearch instance URL | Yes |
ES_API_KEY | Elasticsearch API key for authentication | No |
ES_USERNAME | Elasticsearch username for basic authentication | No |
ES_PASSWORD | Elasticsearch password for basic authentication | No |
ES_CA_CERT | Path to custom CA certificate for Elasticsearch SSL/TLS | No |
ES_SSL_SKIP_VERIFY | Set to '1' or 'true' to skip SSL certificate verification | No |
ES_PATH_PREFIX | Path prefix for Elasticsearch instance exposed at a non-root path | No |
ES_VERSION | Server assumes Elasticsearch 9.x. Set to 8 target Elasticsearch 8.x | No |
[!NOTE]
If you want to modify or extend the MCP Server, follow these local development steps.
nvm use
npm install
npm run build
Edit Config
and add a new MCP Server with the following configuration:{
"mcpServers": {
"elasticsearch-mcp-server-local": {
"command": "node",
"args": [
"/path/to/your/project/dist/index.js"
],
"env": {
"ES_URL": "your-elasticsearch-url",
"ES_API_KEY": "your-api-key",
"OTEL_LOG_LEVEL": "none"
}
}
}
}
ES_URL=your-elasticsearch-url ES_API_KEY=your-api-key npm run inspector
This will start the MCP Inspector, allowing you to debug and analyze requests. You should see:
Starting MCP inspector...
Proxy server listening on port 3000
🔍 MCP Inspector is up and running at http://localhost:5173 🚀
We welcome contributions from the community! For details on how to contribute, please see Contributing Guidelines.
[!TIP]
Here are some natural language queries you can try with your MCP Client.
[!WARNING]
Avoid using cluster-admin privileges. Create dedicated API keys with limited scope and apply fine-grained access control at the index level to prevent unauthorized data access.
You can create a dedicated Elasticsearch API key with minimal permissions to control access to your data:
POST /_security/api_key
{
"name": "es-mcp-server-access",
"role_descriptors": {
"mcp_server_role": {
"cluster": [
"monitor"
],
"indices": [
{
"names": [
"index-1",
"index-2",
"index-pattern-*"
],
"privileges": [
"read",
"view_index_metadata"
]
}
]
}
}
}
This project is licensed under the Apache License 2.0.
If you encounter issues, feel free to open an issue on the GitHub repository.
elastic/mcp-server-elasticsearch
March 24, 2025
July 6, 2025
JavaScript