MCP Directory

Elasticsearch/OpenSearch MCP Server

Search, analyze, and manage Elasticsearch & OpenSearch clusters through MCP tools.

Unverified
stdio (local)
API key
Python
View repo 290

Add to your client

Copy the config for your MCP client and paste it into its config file.

Install / run
uvx elasticsearch-mcp-server

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "elasticsearch-opensearch-mcp-server": {
      "command": "uvx",
      "args": [
        "elasticsearch-mcp-server"
      ],
      "env": {
        "ELASTICSEARCH_HOSTS": "https://localhost:9200",
        "ELASTICSEARCH_USERNAME": "elastic",
        "ELASTICSEARCH_PASSWORD": "test123"
      }
    }
  }
}

Requires `uv` (the Python package runner). Install it from https://docs.astral.sh/uv/ if `uvx` is not found.

Step-by-step guides: Add to Claude Desktop · Add to Cursor · Add to Windsurf

Before you start

  • uv / uvx (or Docker) to run the server
  • A reachable Elasticsearch or OpenSearch cluster (e.g. via the provided docker-compose files)
  • Credentials: basic auth (username/password) or an Elasticsearch API key

About Elasticsearch/OpenSearch MCP Server

A Model Context Protocol server implementation that lets AI clients interact with Elasticsearch and OpenSearch clusters. It enables searching documents, analyzing indices, managing data streams/aliases/analyzers, and monitoring cluster health through a dedicated set of MCP tools, with support for multiple named clusters and configurable safety controls.

Tools & capabilities (20)

general_api_request

Perform a general HTTP API request for any Elasticsearch/OpenSearch API that does not have a dedicated tool.

list_indices

List all indices.

get_index

Return information (mappings, settings, aliases) about one or more indices.

create_index

Create a new index.

delete_index

Delete an index.

create_data_stream

Create a new data stream (requires a matching index template).

get_data_stream

Get information about one or more data streams.

delete_data_stream

Delete one or more data streams and their backing indices.

search_documents

Search for documents.

index_document

Create or update a document in an index.

get_document

Get a document by ID.

delete_document

Delete a document by ID.

delete_by_query

Delete documents matching the provided query.

get_cluster_health

Return basic information about the health of the cluster.

get_cluster_stats

Return a high-level overview of cluster statistics.

list_aliases

List all aliases.

get_alias

Get alias information for a specific index.

put_alias

Create or update an alias for a specific index.

delete_alias

Delete an alias for a specific index.

analyze_text

Analyze text using a specified analyzer or custom analysis chain; useful for debugging search queries and understanding tokenization.

What this server can do

Elasticsearch/OpenSearch MCP Server provides tools for these capabilities — tap one to see every MCP server that does the same:

Search the web

When to use it

  • Let an AI assistant run full-text and structured searches over Elasticsearch/OpenSearch indices
  • Inspect and manage indices, data streams, and aliases conversationally
  • Monitor cluster health and statistics during operations
  • Debug search relevance by analyzing how text is tokenized
  • Operate across multiple named clusters (e.g. prod/staging) from one MCP client

Security notes

For HTTP transports (SSE/Streamable HTTP) set MCP_API_KEY to require a Bearer token; if unset, the server is accessible without authentication, which is a network security risk. The stdio transport uses local process communication and needs no auth. VERIFY_CERTS defaults to false. Use DISABLE_HIGH_RISK_OPERATIONS=true (or DISABLE_OPERATIONS) to hide write/delete tools for read-only deployments. Credentials (passwords / API keys) are passed via environment variables.

Elasticsearch/OpenSearch MCP Server FAQ

Which Elasticsearch/OpenSearch versions are supported?

Elasticsearch 7.x, 8.x, and 9.x via package variants (elasticsearch-mcp-server-es7, elasticsearch-mcp-server for 8.x, elasticsearch-mcp-server-es9), and OpenSearch 1.x/2.x/3.x via opensearch-mcp-server.

What transports are supported?

stdio (default), SSE, and Streamable HTTP. Use the --transport flag (sse or streamable-http) with optional --host, --port, and --path.

How do I make a deployment read-only?

Set DISABLE_HIGH_RISK_OPERATIONS=true to completely hide all write/delete tools from the client, or set DISABLE_OPERATIONS to a comma-separated list of specific operations to disable.

How is the HTTP server secured?

Set MCP_API_KEY and clients must send an Authorization: Bearer <MCP_API_KEY> header. Authentication applies only to HTTP transports; if MCP_API_KEY is unset the server is accessible without authentication.

Can I connect to more than one cluster?

Yes. Set ELASTICSEARCH_CLUSTERS (or OPENSEARCH_CLUSTERS) to a JSON object of named clusters, or point ELASTICSEARCH_CLUSTERS_FILE at a JSON file. Each tool accepts an optional cluster parameter, falling back to DEFAULT_CLUSTER.

#elasticsearch#opensearch#search#database#indexing#cluster-management

Alternatives to Elasticsearch/OpenSearch MCP Server

Compare all alternatives →
Fetch (Reference)
Search & Web
87k

Official MCP reference server that fetches a URL and returns its content as clean Markdown, with chunking.

Verified
stdio (local)
No auth
Python
2 tools
Updated 20 days agoRepo
Firecrawl
Search & Web
6.6k

Official Firecrawl MCP server — scrape, crawl, map, search, and structured extraction for any LLM client.

Verified
stdio (local)
API key
TypeScript
8 tools
Updated 18 days agoRepo
Exa Search
Search & Web
4.6k

Exa's neural web search and crawling MCP server — runs locally via npx or as a hosted remote endpoint.

Verified
stdio (local)
API key
TypeScript
6 tools
Updated 19 days agoRepo

Compare Elasticsearch/OpenSearch MCP Server with:

vs Fetch (Reference)vs Firecrawlvs Exa Searchvs ArXiv MCP Server