Opensearch Dashboards Mcp Server Py
FreeNot checkedMCP server for OpenSearch Dashboards API — saved objects CRUD, PPL/DQL queries, visualizations, and observability
About
MCP server for OpenSearch Dashboards API — saved objects CRUD, PPL/DQL queries, visualizations, and observability
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
Installing Opensearch Dashboards Mcp Server Py
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/eemijuntunen/opensearch-dashboards-mcp-server-pyFAQ
Is Opensearch Dashboards Mcp Server Py MCP free?
Yes, Opensearch Dashboards Mcp Server Py MCP is free — one-click install via Unyly at no cost.
Does Opensearch Dashboards Mcp Server Py need an API key?
No, Opensearch Dashboards Mcp Server Py runs without API keys or environment variables.
Is Opensearch Dashboards Mcp Server Py hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Opensearch Dashboards Mcp Server Py in Claude Desktop, Claude Code or Cursor?
Open Opensearch Dashboards Mcp Server Py 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
GitHub
PRs, issues, code search, CI status
by GitHubFilesystem
Secure file operations with configurable access controls.
Memory
Knowledge graph-based persistent memory system.
Template MCP Server
A CLI tool to create a new Model Context Protocol server project with TypeScript support, dual transport options, and an extensible structure
by mcpdotdirectCompare Opensearch Dashboards Mcp Server Py with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All development MCPs
