OpenSearch Dashboards Server
FreeNot checkedAn MCP server for managing OpenSearch Dashboards, enabling AI assistants to create, manage, and inspect dashboards, visualizations, saved objects, and plugin fe
About
An MCP server for managing OpenSearch Dashboards, enabling AI assistants to create, manage, and inspect dashboards, visualizations, saved objects, and plugin features.
README
An MCP server for OpenSearch Dashboards that enables AI assistants to create, manage, and inspect dashboards, visualizations, saved objects, and plugin features.
This is a companion to opensearch-mcp-server-py, which covers the OpenSearch cluster/data plane. This project covers the Dashboards UI/management plane.
Features
- Saved Objects CRUD (dashboards, visualizations, index patterns, saved searches)
- Dashboard and Visualization management
- Auto-detection of installed plugins (alerting, anomaly detection, etc.)
- Category-based tool filtering
- Support for stdio and streaming (SSE) transports
- Basic auth, API token, and cookie/session authentication
Installation
pip install opensearch-dashboards-mcp-server
Quick Start
# Using environment variables
export OSD_URL=https://localhost:5601
export OSD_USERNAME=admin
export OSD_PASSWORD=admin
opensearch-dashboards-mcp-server
# Using config file
opensearch-dashboards-mcp-server --config example_config.yml
Claude Desktop Integration
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"opensearch-dashboards": {
"command": "opensearch-dashboards-mcp-server",
"env": {
"OSD_URL": "https://localhost:5601",
"OSD_USERNAME": "admin",
"OSD_PASSWORD": "admin"
}
}
}
}
Tool Categories
| Category | Tools | Default |
|---|---|---|
core_tools |
Saved Objects, Dashboards, Visualizations, Index Patterns, Short URLs | Enabled |
alerting |
Monitors, Alerts | Auto-detected |
anomaly_detection |
Detectors, Results | Auto-detected |
observability |
Notebooks | Auto-detected |
index_management |
ISM Policies | Auto-detected |
security |
Tenants, Roles, Role Mappings | Auto-detected |
workspaces |
Workspace CRUD | Auto-detected |
sample_data |
Sample dataset install/uninstall | Auto-detected |
data_importer |
File/text import, preview | Auto-detected |
Enable/disable categories via env vars:
export OSD_ENABLED_CATEGORIES=core_tools,alerting,anomaly_detection
export OSD_DISABLED_CATEGORIES=security
Local Development
# OpenSearch 2.19.0 (default)
docker compose up -d
# OpenSearch 3.5.0
OPENSEARCH_VERSION=3.5.0 docker compose up -d
# Verify
curl http://localhost:9200 # OpenSearch
curl http://localhost:5601 # Dashboards
Supported Versions
- OpenSearch / Dashboards 2.x (tested with 2.19.0)
- OpenSearch / Dashboards 3.x (tested with 3.5.0)
License
Apache-2.0
from github.com/eemijuntunen/opensearch-dashboards-mcp-server-py
Install OpenSearch Dashboards Server in Claude Desktop, Claude Code & Cursor
unyly install opensearch-dashboards-mcp-serverInstalls into Claude Desktop, Claude Code, Cursor & VS Code — handles npx, uvx and build-from-source repos for you.
First time? Get the CLI: curl -fsSL https://unyly.org/install | sh
Or configure manually
Run in your terminal:
claude mcp add opensearch-dashboards-mcp-server -- uvx --from git+https://github.com/eemijuntunen/opensearch-dashboards-mcp-server-py opensearch-dashboards-mcp-serverFAQ
Is OpenSearch Dashboards Server MCP free?
Yes, OpenSearch Dashboards Server MCP is free — one-click install via Unyly at no cost.
Does OpenSearch Dashboards Server need an API key?
No, OpenSearch Dashboards Server runs without API keys or environment variables.
Is OpenSearch Dashboards Server hosted or self-hosted?
A hosted option is available: Unyly runs the server in the cloud, no local setup required.
How do I install OpenSearch Dashboards Server in Claude Desktop, Claude Code or Cursor?
Open OpenSearch Dashboards Server on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
by modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
by xuzexin-hzCompare OpenSearch Dashboards Server with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All ai MCPs
