Skip to main content
Glama
OpenSearch MCP Server

OpenSearch MCP Server

by seohyunjun

OpenSearch MCP Server

Overview

This Repository Fork of elastic-mcp-server and Converted to opensearch-mcp-server MCP Server. It is a Model Context Protocol (MCP) server implementation that provides opensearch interaction. This server enables searching documents, analyzing indices, and managing cluster through a set of tools.

A Model Context Protocol (MCP) server implementation that provides opensearch interaction. This server enables searching documents, analyzing indices, and managing cluster through a set of tools.

Related MCP server: Elasticsearch MCP Server

Features

Index Operations

  • list_indices: List all indices in the Opensearch cluster.

  • get_mapping: Retrieve the mapping configuration for a specific index.

  • get_settings: Get the settings configuration for a specific index.

Document Operations

  • search_documents: Search documents in an index using Opensearch Query DSL.

Cluster Operations

  • get_cluster_health: Get health status of the cluster.

  • get_cluster_stats: Get statistical information about the cluster.

Start Opensearch Cluster

Start the Opensearch cluster using Docker Compose:

docker-compose up -d

This will start a 3-node Opensearch cluster and Kibana. Default Opensearch username opensearch, password test123.

You can access Kibana from http://localhost:5601.

Usage with Claude Desktop

Using uv with local development

Using uv requires cloning the repository locally and specifying the path to the source code. Add the following configuration to Claude Desktop's config file claude_desktop_config.json.

you need to change path/to/src/opensearch_mcp_server to the path where you cloned the repository.

{
  "mcpServers": {
    "opensearch": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/src/opensearch_mcp_server",
        "run",
        "opensearch-mcp-server"
      ],
      "env": {
        "OPENSEARCH_HOST": "https://localhost:9200",
        "OPENSEARCH_USERNAME": "opensearch",
        "OPENSEARCH_PASSWORD": "test123",
        "DASHBOARDS_HOST": "https://localhost:5601"
      }
    }
  }
}
  • On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • On Windows: %APPDATA%/Claude/claude_desktop_config.json

Restart Claude Desktop to load the new MCP server.

Now you can interact with your Opensearch cluster through Claude using natural language commands like:

  • "List all indices in the cluster"

  • "How old is the student Bob?"

  • "Show me the cluster health status"

License

This project is licensed under the Apache License Version 2.0 - see the LICENSE file for details.

Available Tools

14 tools
generate_discover_urlC

Generate OpenSearch Dashboards Discover view URL

Inputs: query (required), index_pattern_id (required), from_time (required), to_time (required).

get_cluster_healthC

Get cluster health status

Inputs: no named parameters.

get_cluster_statsC

Get cluster statistics

Inputs: no named parameters.

get_hot_threadsC

Check hot threads on nodes

Inputs: no named parameters.

get_index_templatesB

Get index template configurations

Inputs: no named parameters.

get_ism_policiesB

Get ISM policies and their configurations

Inputs: no named parameters.

get_mappingD

Get index mapping

Inputs: index (required).

get_recovery_statusB

Get recovery status and estimated completion time

Inputs: no named parameters.

get_settingsC

Get index settings

Inputs: index (required).

get_shard_allocationC

Get index shard allocation distribution

Inputs: latest_index (required).

get_tasksC

Get current tasks in cluster

Inputs: no named parameters.

list_index_patternsB

List OpenSearch Dashboards index patterns2

Inputs: no named parameters.

list_indicesB

List all indices in the Opensearch cluster

Inputs: no named parameters.

search_documentsC

Search documents in an opensearch index with a custom query

Inputs: index (required), body (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.1/5.0

    Scored across 14 tools

    Disambiguation5/5

    Every tool has a clearly distinct purpose targeting specific OpenSearch operations. There is no overlap between tools like get_cluster_health (health status), get_mapping (index structure), and search_documents (document queries). Each tool name precisely indicates its unique function within the OpenSearch domain.

    Naming Consistency5/5

    All tools follow a consistent verb_noun naming pattern throughout. The pattern is predominantly 'get_' for retrieval operations and 'list_' for listing operations, with specific exceptions like 'generate_' and 'search_' that maintain the same structure. No mixing of conventions like camelCase or snake_case variations.

    Tool Count5/5

    With 14 tools, this server is well-scoped for OpenSearch operations, covering monitoring, configuration, and data querying aspects. Each tool earns its place by addressing distinct needs like cluster health, index management, and document search, without being overly sparse or bloated.

    Completeness4/5

    The tool set provides strong coverage for monitoring, configuration retrieval, and search operations in OpenSearch. Minor gaps exist, such as the absence of tools for creating or updating resources (e.g., indices, policies), but agents can still perform core read and diagnostic workflows effectively.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      A
      maintenance
      Facilitates interaction with Elasticsearch clusters by allowing users to perform index operations, document searches, and cluster management via a Model Context Protocol server and natural language commands.
      20
      317
      Apache 2.0
    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that enables LLMs to interact with Elasticsearch clusters, allowing them to manage indices and execute search queries using natural language.
      2
      -
    • A
      license
      A
      quality
      B
      maintenance
      MCP server for OpenSearch that enables AI assistants to interact with OpenSearch clusters through a standardized interface for search, index management, and cluster operations.
      9
      40,158 PyPI
      158
      Apache 2.0
    • A
      license
      B
      quality
      D
      maintenance
      opensearch-mcp-server-py is a Model Context Protocol (MCP) server for OpenSearch that enables AI assistants to interact with OpenSearch clusters. It provides a standardized interface for AI models to perform operations like searching indices, retrieving mappings, and managing shards through both stdio and streaming (SSE/Streamable HTTP) protocols.
      11
      Apache 2.0

    Appeared in Searches