How to connect Elasticsearch to ChatGPT

1. 1. Enable Elasticsearch in Metorial

   In your Metorial portal, enable the Elasticsearch MCP server and sign in with the account that owns the data. Access stays governed by your team policies.

2. 2. Add a custom MCP server

   On ChatGPT web, open Plugins, select +, then Add custom MCP server.

3. 3. Paste your Metorial MCP URL

   Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>), choose OAuth and accept the risk notice.

4. 4. Create and install the plugin

   Select Create as a plugin, install it and sign in to load Elasticsearch tools.

• Cluster Health: Get the health status and key metrics of the Elasticsearch cluster including node count, shard allocation status, and pending tasks.
• List Indices: List all indices in the Elasticsearch cluster with their health status, document count, and storage size.
• Get Document: Retrieve one or more known Elasticsearch documents by ID.
• Bulk Operations: Perform multiple index, create, update, or delete operations in a single API call.
• Index Document: Create or replace a document in an Elasticsearch index.
• Update Document: Partially update an existing document in an Elasticsearch index.
• Manage Index: Create, configure, open, close, or delete an Elasticsearch index.
• Search Documents: Search and query documents in Elasticsearch using the full Query DSL.
• Manage Watch: Create, update, delete, execute, activate, or deactivate Watcher alerts.
• Manage Alias: Create, delete, or list index aliases.
• Graph Explore: Discover relationships between terms in an Elasticsearch index.
• ES|QL Query: Execute an ES|QL query to filter, transform, and analyze data stored in Elasticsearch.
• Manage Snapshot: Create, restore, delete, or retrieve snapshots and snapshot repositories for cluster backups.
• Reindex: Copy documents from one index to another, optionally applying a query filter or transformations via a script.
• Run Inference: Execute a machine learning inference task using a configured inference endpoint.
• And 5 more on the Elasticsearch MCP server page.

• Type @ and pick the plugin. The selection applies to that message only, so @mention it again when a follow-up needs fresh Elasticsearch data.
• For write actions, ChatGPT may ask you to confirm first, depending on the app permissions and the action.
• Once published for a workspace, ChatGPT keeps a snapshot of the tool list. When your team adds Elasticsearch tools in Metorial, an admin refreshes the actions in Workspace settings before they appear.
• You can use several apps in one prompt, for example read Elasticsearch data and then create a ticket in another app.

Add custom MCP server is missing

Workspace policy controls it. On Enterprise and Edu, an admin grants the permission to create plugins with MCPs; ask them to enable it for you.

The plugin exists but no tools appear

Creating the plugin is not enough: install it from your plugins, then start a new conversation so ChatGPT loads its tools.

ChatGPT answers without using the tools

Pick the plugin with @ in the composer and name the action you want, for example "use Metorial to look up the latest ticket".

Based on the ChatGPT MCP documentation.