opensearch-mcp-server-py
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AWS_REGION | No | AWS region. | |
| AWS_IAM_ARN | No | IAM role ARN. | |
| AWS_PROFILE | No | AWS profile name. | |
| OPENSEARCH_URL | No | OpenSearch endpoint URL. | |
| OPENSEARCH_NO_AUTH | No | Connect without authentication. | |
| OPENSEARCH_TIMEOUT | No | Connection timeout in seconds. | |
| OPENSEARCH_PASSWORD | No | Password for basic auth. | |
| OPENSEARCH_USERNAME | No | Username for basic auth. | |
| MEMORY_TOOLS_ENABLED | No | Enable memory tools. | |
| OPENSEARCH_SSL_VERIFY | No | SSL certificate verification. | |
| AWS_OPENSEARCH_SERVERLESS | No | Use OpenSearch Serverless. | |
| OPENSEARCH_ENABLED_CATEGORIES | No | Categories to enable. | |
| OPENSEARCH_DISABLED_CATEGORIES | No | Categories to disable. | |
| OPENSEARCH_MEMORY_CONTAINER_ID | No | Memory container ID for agentic memory. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ListIndexToolA | Lists indices in the OpenSearch cluster. If an index name or pattern is specified, return only information about the provided index or index pattern. The include_detail flag controls output: if False, returns only index name(s); if True (default), returns full metadata. |
| IndexMappingToolC | Retrieves index mapping and setting information for an index in OpenSearch |
| SearchIndexToolB | Searches an index using a query written in query domain-specific language (DSL) in OpenSearch. PREREQUISITE: You need to know the mappings of the index before constructing queries. |
| GetShardsToolB | Gets information about shards in OpenSearch |
| GenericOpenSearchApiToolA | A flexible tool for calling any OpenSearch API endpoint. Supports all HTTP methods with custom paths, query parameters, request bodies, and headers. Use this when you need to access OpenSearch APIs that don't have dedicated tools, or when you need more control over the request. Leverages your knowledge of OpenSearch API documentation to construct appropriate requests. |
| ClusterHealthToolC | Returns basic information about the health of the cluster. |
| CountToolB | Returns number of documents matching a query. |
| MsearchToolB | Allows to execute several search operations in one request. |
| ExplainToolB | Returns information about why a specific document matches (or doesn't match) a query. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools target distinct actions such as listing indices, retrieving mappings, searching, counting, and checking cluster health. GenericOpenSearchApiTool intentionally overlaps with every dedicated tool, and MsearchTool overlaps somewhat with SearchIndexTool, but the descriptions provide enough guidance to choose correctly.
All tool names use PascalCase with a Tool suffix, and most follow a Verb+Noun pattern like ListIndexTool, SearchIndexTool, and GetShardsTool. IndexMappingTool and ClusterHealthTool lack explicit action verbs, and MsearchTool uses an abbreviated name, so the pattern is not perfectly consistent.
Nine tools is a well-scoped count for an OpenSearch server covering search, mappings, cluster health, shards, counts, and a generic API fallback. Each dedicated tool earns its place, and the count is comfortably within the ideal range.
The dedicated tools cover common read, search, and monitoring workflows well, and GenericOpenSearchApiTool provides an escape hatch for any unsupported endpoint. However, common operations like creating/deleting indices or document-level CRUD lack dedicated first-class tools, so coverage relies partly on the generic fallback.