Connect Elasticsearch to Claude Code

Let Claude run scoped reads and writes against your Elasticsearch indices. From the terminal, inside the sessions where you already work.

Build my connector Talk to us

How do you connect Elasticsearch to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Elasticsearch, you add a Elasticsearch MCP server: a small hosted service that exposes Elasticsearch's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Elasticsearch account. No API keys pasted into config files.

claude mcp add --transport http elasticsearch https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Elasticsearch once connected?

Full read-write Elasticsearch access lets Claude index a new document, update or correct fields on a record, run a bulk operation, and adjust an index or alias once you approve. The work that used to mean switching into Kibana or a REST client happens where you are already describing the change in plain language.

Index a new document into a specified index with given field values
Update or correct fields on records matching a stated query after approval
Run a bulk operation to index or update many documents at once
Create an index or update a mapping to support a new field
Reassign or update an alias to point at a different index once you confirm
Delete documents matching a precise query after you approve it

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Elasticsearch access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Elasticsearch API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Elasticsearch changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Elasticsearch connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Elasticsearch connector work in claude.ai and Claude Code?

Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Elasticsearch account, so access always matches what that person can already see and do.

Do I need to host or maintain anything myself?

No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Elasticsearch's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.

Is it safe to give a coding agent write access to Elasticsearch?

Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Elasticsearch account it signs in with. Revoking access is one click in Elasticsearch.

More on the Elasticsearch connector

Elasticsearch connector for claude.ai Amazon Redshift + Claude Code Looker + Claude Code Metabase + Claude Code

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.

Build my connector Talk to us