# Elasticsearch for AI agents. Managed auth, ready-made tools.

> Search indices, read and write documents and check mappings in Elasticsearch on behalf of each of your users.

- Page: https://www.agent200.com/connectors/elasticsearch/
- Category: Search and data
- Authentication: Managed OAuth
- Identifier in code: `elasticsearch`
- Create an API key: https://agent200.com/platform/apikeys/
- Updated: 2026-11-18

## Instructions for AI agents

Connector: Elasticsearch, through Agent200. In code: "elasticsearch".
What it does: Search indices, read and write documents and check mappings in Elasticsearch on behalf of each of your users.
Page: https://www.agent200.com/connectors/elasticsearch/

1. Get an Agent200 API key. If the developer has none, send them to https://agent200.com/platform/apikeys/ and ask them to choose "Create an API key". Read the key from the AGENT200_API_KEY environment variable. Never ask for it in chat, and never write it into code, prompts or logs.
2. Sign-in is managed OAuth. Each end user approves access once, on Elasticsearch's own page, through the authorization link Agent200 returns. Never ask a user for a Elasticsearch password or token in chat.
3. Give every request a stable id for the end user. Agent200 uses only that user's own connection.
4. Read tools: elasticsearch_list_indices, elasticsearch_get_mapping, elasticsearch_search, elasticsearch_get_document. Write tools: elasticsearch_index_document, elasticsearch_delete_document. Name "elasticsearch" in the tools of a request; the model decides which tool to call.
5. Stay within the project's settings. If a tool is turned off or a call is refused, tell the user. Do not work around it.
6. Before a write, confirm with the user, unless they asked for that exact change.
7. For setup with a specific framework, follow its guide:
   https://www.agent200.com/connectors/elasticsearch/framework/claude/
   https://www.agent200.com/connectors/elasticsearch/framework/chatgpt/
   https://www.agent200.com/connectors/elasticsearch/framework/claude-code/
   https://www.agent200.com/connectors/elasticsearch/framework/muse/
   https://www.agent200.com/connectors/elasticsearch/framework/grok-bot/
   https://www.agent200.com/connectors/elasticsearch/framework/openai-dots/
   https://www.agent200.com/connectors/elasticsearch/framework/claude-duet/
   https://www.agent200.com/connectors/elasticsearch/framework/hermes-agent/
   https://www.agent200.com/connectors/elasticsearch/framework/openclaw/

The code on the connector page is a conceptual example of the SDK. SDK reference: https://docs.igpt.ai/

## About

With the Elasticsearch connector, your agent works with each user's own Elasticsearch deployment. It can list indices, check their mappings, run searches, read documents, and add or delete documents, using only the tools your project allows.

Elasticsearch is a search and analytics engine for storing and querying large amounts of data.

## Elasticsearch tools

- **List indices** (`elasticsearch_list_indices`, read): List the indices in the cluster with their size and health.
- **Get a mapping** (`elasticsearch_get_mapping`, read): Get the field mapping of an index.
- **Search** (`elasticsearch_search`, read): Run a search query against an index.
- **Get a document** (`elasticsearch_get_document`, read): Get a document by its ID.
- **Index a document** (`elasticsearch_index_document`, write): Add or replace a document in an index.
- **Delete a document** (`elasticsearch_delete_document`, write): Delete a document by its ID.

## Limits you can set

**Turn single tools on or off.** Let the agent search and add documents, and switch off `elasticsearch_delete_document` so it can never remove one.

**Restrict what the agent reaches.** Choose the endpoints and scopes a project may use, for example search but not writes. A call outside them is refused.

## Get started

### Step 1: Set up the SDK

Add the Agent200 SDK to the codebase you already have and authenticate with your API key. The key covers every connector enabled for the project.

File `agent.js`:

```js
// One Agent200 API key covers every connector enabled for the project.
const agent200 = new Agent200({
  apiKey: process.env.AGENT200_API_KEY,
});
```

(Conceptual example of the Agent200 SDK.)

### Step 2: Let your user connect Elasticsearch

Each end user authorizes their own Elasticsearch account once. Agent200 runs the OAuth flow, handles the callback, stores the tokens and refreshes them.

File `connect.js`:

```js
// Each end user authorizes their own Elasticsearch account, once.
const connection = await agent200
  .user("user_123")
  .connect("elasticsearch");

if (connection.authorizationUrl) {
  // Show this link to your user; Agent200 handles the rest.
  console.log(connection.authorizationUrl);
}
```

(Conceptual example of the Agent200 SDK.)

### Step 3: Run with the Elasticsearch tools

Name the user, the model and the tools. The model decides which Elasticsearch tools to call, and Agent200 executes them with that user's connection.

File `run.js`:

```js
const result = await agent200
  .user("user_123")
  .run({
    model: "openai/gpt-5.6-sol",
    input: "Search the logs index for errors from the checkout service today",
    tools: ["elasticsearch"],
  });

console.log(result.output);
```

(Conceptual example of the Agent200 SDK.)

## Sign-in and permissions

**Who signs in.** Each of your users, once, by connecting their own Elasticsearch deployment. Each connection is their own.

**What access is requested.** The connection acts with the privileges of the credentials the user connects with, such as reading an index or writing documents. Users can revoke the connection later from their Elasticsearch or Elastic Cloud settings.

## Example requests

- "Search the logs index for errors from the checkout service today"
- "What fields does the products index have"
- "How many orders were indexed yesterday"

## Guides: Elasticsearch with your AI framework

- [Elasticsearch + Claude](https://www.agent200.com/connectors/elasticsearch/framework/claude.md): Set up Elasticsearch for Claude with Agent200, then check which tools are available to your agent.
- [Elasticsearch + ChatGPT](https://www.agent200.com/connectors/elasticsearch/framework/chatgpt.md): Set up Elasticsearch for ChatGPT with Agent200, then check which tools are available to your agent.
- [Elasticsearch + Claude Code](https://www.agent200.com/connectors/elasticsearch/framework/claude-code.md): Set up Elasticsearch for Claude Code with Agent200, then check which tools are available to your agent.
- [Elasticsearch + Muse](https://www.agent200.com/connectors/elasticsearch/framework/muse.md): Set up Elasticsearch for Muse with Agent200, then check which tools are available to your agent.
- [Elasticsearch + Grok Bot](https://www.agent200.com/connectors/elasticsearch/framework/grok-bot.md): Set up Elasticsearch for Grok Bot with Agent200, then check which tools are available to your agent.
- [Elasticsearch + OpenAI Dots](https://www.agent200.com/connectors/elasticsearch/framework/openai-dots.md): Set up Elasticsearch for OpenAI Dots with Agent200, then check which tools are available to your agent.
- [Elasticsearch + Claude Duet](https://www.agent200.com/connectors/elasticsearch/framework/claude-duet.md): Set up Elasticsearch for Claude Duet with Agent200, then check which tools are available to your agent.
- [Elasticsearch + Hermes Agent](https://www.agent200.com/connectors/elasticsearch/framework/hermes-agent.md): Set up Elasticsearch for Hermes Agent with Agent200, then check which tools are available to your agent.
- [Elasticsearch + OpenClaw](https://www.agent200.com/connectors/elasticsearch/framework/openclaw.md): Set up Elasticsearch for OpenClaw with Agent200, then check which tools are available to your agent.

## FAQ

### Who handles the Elasticsearch OAuth flow and the tokens?

Agent200. It runs the authorization, handles the callback on its own domain, stores the tokens and refreshes them. You do not build or maintain an OAuth integration for Elasticsearch.

### Does my agent act as the end user?

Within what that user authorized, yes. Every request names an end user, and Agent200 uses only that user's Elasticsearch connection, never another user's. It cannot reach anything the user or Elasticsearch has not authorized.

### Can I limit what my agent can do in Elasticsearch?

Yes. You choose which services, endpoints and authorization scopes are allowed in your Agent200 configuration, and the agent works only within them.

## Related connectors

- [Tavily](https://www.agent200.com/connectors/tavily.md): Web search built for agents, reached with your Agent200 API key.
- [Exa](https://www.agent200.com/connectors/exa.md): Search the web by meaning, read page contents and find similar pages, reached with your Agent200 API key.
- [Firecrawl](https://www.agent200.com/connectors/firecrawl.md): Scrape pages into Markdown, crawl and map sites, and extract structured data, reached with your Agent200 API key.
- [Brave Search](https://www.agent200.com/connectors/brave-search.md): Search the web, news, images and videos from Brave's independent index, reached with your Agent200 API key.

---

Agent200: https://www.agent200.com/ · API keys: https://agent200.com/platform/apikeys/ · Docs: https://docs.igpt.ai/
