Strawgate's Elasticsearch MCP project
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"strawgate-es-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# strawgate_es_mcp Strawgate's Unofficial MCP Server for Elasticsearch. Use at your own risk. This is not an official Elasticsearch product. This MCP Server will probably break your Elasticsearch cluster. Do not use it. This project provides a Model Context Protocol (MCP) server implemented in Python using `fastmcp`. Its primary purpose is to expose a wide range of Elasticsearch client functionalities as callable MCP tools, allowing for interaction with an Elasticsearch cluster via the MCP. ## Features - **Elasticsearch Tooling**: Exposes numerous Elasticsearch client APIs as MCP tools, including: - CAT APIs (allocation, aliases, count, indices, nodes, shards, etc.) - Cluster APIs (health, state, stats) - Nodes APIs (info, stats) - Indices APIs (create/get data stream, stats, resolve index) - ILM and SLM APIs (get/explain lifecycle, get status, get stats) - Shutdown APIs (get node) - Search API - **CLI**: A CLI for the MCP Server. - **Extensible**: Easily add new Elasticsearch client methods as MCP tools or integrate with other MCP tools. - **Sample Script**: Includes `sample_multisearch.py` to demonstrate using the Elasticsearch Python client for multi-searches. - **Testing**: Includes unit tests for the exposed tools and sample scripts using `pytest`. ## Setup in Windsurf On the right in the cascade window press the hammer icon and add a server with the following configuration: ```json { "mcpServers": { "es-mcp": { "command": "uvx", "args": [ "--from", "git+https://github.com/strawgate/py-mcp-collection.git#subdirectory=es-mcp", "es-mcp" ], "env": { "ES_HOST": "https://my-cloud-cluster:443", "ES_API_KEY": "MYCOOLAPIKEY" } } } } ``` ## VS Code McpServer Usage 1. Open the command palette (Ctrl+Shift+P or Cmd+Shift+P). 2. Type "Settings" and select "Preferences: Open …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.