Provides read-only search and aggregation capabilities for Elasticsearch, including listing indices and retrieving mappings, enabling agents to query and inspect Elasticsearch data.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-elasticsearch list all indices and show me the mapping for the logs index"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Elasticsearch MCP Server (Model Context Protocol) - read-only search only.
Only exposes read-only operations:
list_indices - List all indices
get_mapping - Get index mapping
search - Execute search/aggregation query
Related MCP server: Elasticsearch MCP Server
python -m mcp_elasticsearch --transport stdio --url http://localhost:9200python -m mcp_elasticsearch --transport sse --host 0.0.0.0 --port 8002 --url http://elasticsearch:9200 [--api-key your-secret-key]All command line arguments can also be set via environment variables:
TRANSPORT - stdio or sse (default: stdio)
HOST - bind host for sse mode (default: 0.0.0.0)
PORT - bind port for sse mode (default: 8002)
ELASTICSEARCH_URL - Elasticsearch URL
API_KEY - Optional API key for client authentication
FROM python:3.11-slim
WORKDIR /app
COPY pyproject.toml poetry.lock ./
RUN poetry install --no-dev --no-root
COPY mcp_elasticsearch/ ./mcp_elasticsearch/
EXPOSE 8002
CMD ["python", "-m", "mcp_elasticsearch"]This server cannot be deployed
Read-only MCP access to sessions, funnels, campaigns, errors, live visitors, and anomalies.
Read-only MCP for identity resolution and write guardrails.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Provides read access to your GKE and Kubernetes resources.
