opensearch-dashboard-mcp
Exposes OpenSearch Dashboards API to manage saved objects (e.g., dashboards), list tenants and index patterns, and perform searches like the Discover app for log querying.
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., "@opensearch-dashboard-mcp list dashboards"
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.
opensearch-dashboard-mcp
MCP server that exposes OpenSearch Dashboards to an LLM client over stdio. Read saved objects, list tenants and index patterns, and query logs like the Discover app — all through the Dashboards API, so it works even when the raw OpenSearch REST API isn't exposed.
Run
uvx opensearch-dashboard-mcp(After publishing to PyPI. For local dev use uvx --from . opensearch-dashboard-mcp.)
Related MCP server: Kibana Dashboard Builder
Configure
Environment variables:
Variable | Default | Purpose |
|
| Base URL |
| — | Basic auth / session-login user |
| — | Basic auth / session-login password |
|
| Verify TLS certs |
| — | If set (e.g. |
| auto | Local port for the tunnel; a free port is picked when unset |
SSH tunnel
When SSH_PROXY_TO is set, the server spawns ssh -N -D <port> <host> before
serving and routes HTTP through the resulting socks5h:// proxy. DNS is resolved
on the remote side, so this reaches targets only visible from a remote network
(e.g. a VPN living inside a container). Requires key-based SSH auth (runs with
BatchMode=yes). The tunnel lives exactly as long as the server.
Use in an MCP client
{
"mcpServers": {
"opensearch-dashboards": {
"command": "uvx",
"args": ["opensearch-dashboard-mcp"],
"env": {
"OPENSEARCH_DASHBOARDS_URL": "http://localhost:5601",
"OPENSEARCH_DASHBOARDS_USERNAME": "admin",
"OPENSEARCH_DASHBOARDS_PASSWORD": "admin"
}
}
}
}Tools
ping()— check connectivity + auth. Hits the security authinfo endpoint; on a 401 with credentials set, performs a session login and re-checks. Returns{connected, authenticated, user, tenants}or the error reason.list_saved_objects(type_="dashboard", per_page=20, tenant=None)— saved objects viasaved_objects/_find, returned as compact{id, title, type}.tenantselects the multi-tenancy tenant (name,"__user__"for the private tenant, orNonefor the user default).get_tenants()— multi-tenancy tenants via the security plugin config API, as{name, description, reserved, hidden}.get_index_patterns(per_page=50)— index patterns (saved objects of typeindex-pattern), as{id, title, time_field}.discover_search(index, query=None, time_from=None, time_to=None, time_field="@timestamp", size=10, fields=None, tenant=None)— fetch documents like the Discover app through the internal search API (/internal/search/opensearch).queryis a Lucene query_string;time_from/time_tofilter a range (now-15m, ISO, …);fieldstrims_sourceto avoid flooding context. Returns{index, total, count, hits}.
Multi-tenancy note: saved objects are stored per tenant. Discover available tenant
names with get_tenants, then pass one as tenant to the other tools.
Develop
uv sync --group dev
uv run opensearch-dashboard-mcp # starts on stdio; Ctrl-D to exit
uv run pytest # tests (add --cov for the 100% gate)Layout: config.py (env → Settings), client.py (async httpx wrapper),
tools.py (tool registrations), server.py (entry point + tunnel), tunnel.py
(SSH SOCKS5 tunnel). See CLAUDE.md for the architecture in depth.
Available Tools
5 toolsdiscover_searchA
Fetch documents like the Discover app.
Runs a search against an index pattern through the internal search API
that OpenSearch Dashboards' Discover uses (/internal/search/opensearch),
so it works even when the raw OpenSearch REST API is not exposed.
index: index-pattern glob, e.g.logs-api-*(discover them vialist_saved_objectswithtype_="index-pattern").query: Lucene query_string, e.g.level:error AND service:api.Nonematches everything.time_from/time_to: range ontime_field, e.g.now-15m/nowor an ISO timestamp. Both optional.time_field: timestamp field to filter/sort on (default@timestamp).size: max hits to return (default 10; keep small — these are logs).fields: restrict_sourceto these fields to avoid flooding the context.Nonereturns the full document.tenant:securitytenantheader; usually unnecessary for raw data.
Returns {index, total, count, hits: [{_id, _index, _source}]} where
total is the full match count (may be an estimate for large indices).
Inputs: index (required), size, query, fields, +4 more. Returns: object
get_index_patternsA
List index patterns configured in OpenSearch Dashboards.
Index patterns are saved objects of type index-pattern. Returns
{id, title, time_field} where title is the pattern glob
(e.g. logs-*) and time_field its time field, if any.
Inputs: per_page. Returns: object
get_tenantsA
List multi-tenancy tenants configured in OpenSearch Dashboards.
Uses the security plugin config API (/api/v1/configuration/tenants),
which returns a map of tenant name -> metadata. Flattened here to a list
of {name, description, reserved, hidden}.
Inputs: no named parameters. Returns: object
list_saved_objectsA
List saved objects of a given type (dashboard, index-pattern, search, ...).
Calls the Dashboards saved_objects/_find API and returns a compact
list of {id, title, type} so the LLM is not flooded with raw fields.
Saved objects are stored per multi-tenancy tenant. tenant selects
which one to read via the securitytenant header:
a tenant name (e.g. "Developers Core", "Global")
"user" for the caller's private tenant
None (default) uses the user's configured default tenant Use the
get_tenantstool to discover available tenant names.
Inputs: type_, tenant, per_page. Returns: object
pingA
Check OpenSearch Dashboards connectivity and authenticate.
Hits the security authinfo endpoint. If unauthenticated (HTTP 401) and credentials are configured, performs a session login and re-checks. Reports {connected, authenticated, user, tenants} or the error reason.
Inputs: no named parameters. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct resource or action: search, index patterns, tenants, saved objects, and connectivity. No overlap in purpose.
All tool names follow a consistent verb_noun pattern (e.g., discover_search, get_index_patterns), and 'ping' is a standard imperative verb, fitting the pattern.
5 tools is well-scoped for a dashboard interaction server, covering essential query and listing operations without being overly numerous.
Covers core read operations (search, list index patterns, tenants, saved objects) but lacks write operations (create/update/delete) and direct retrieval of saved object details, which are minor gaps for a query-focused tool.
Maintenance
Related MCP Connectors
Lets AI agents analyze API metrics, request logs, and traces, and manage apps and alerts.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Discover Frontier inference capabilities and read sanitized usage through read-only tools.
Discover, compare, route, and execute machine-accessible capabilities for AI agents.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to interact with Kibana dashboards, visualizations, and Elasticsearch data through read-only resources and executable tools for searching logs, exporting dashboards, and querying data.74MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to create and manage Kibana dashboards, Lens visualizations, and data views via the Kibana Saved Objects API. It allows for programmatically listing existing resources and assembling new visualizations into dashboards through natural language commands.-
- FlicenseNot gradedqualityDmaintenanceEnables LLMs to interact with OpenSearch clusters to monitor cluster health, manage indices, and perform data searches. It provides a standardized interface for real-time OpenSearch operations within MCP-compatible environments like Open WebUI.-
- AlicenseNot gradedqualityAmaintenanceEnables AI assistants to interact with OpenSearch clusters for searching indices, retrieving mappings, and managing shards through the MCP protocol.Apache 2.0