Elasticsearch for AI agents
Elasticsearch is a distributed search and analytics engine used to index, search, and analyze large volumes of data in real time. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Elasticsearch.
Query an index for records
Query an index to find documents matching a search request from a user.
Check an index's schema
Get an index's schema to confirm which fields are searchable before building a query.
Read-only cluster health checks
Ping the cluster as a read-only check before running a heavier query against it.
4 Elasticsearch actions, graded by risk.
Every Elasticsearch action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
4Look things up. Allowed by default.
- elasticsearch.query_indexQuery Index
- elasticsearch.list_indicesList Indices
- elasticsearch.get_index_schemaGet Index Schema
- elasticsearch.ping_clusterPing Cluster
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Elasticsearch in three steps.
- 01Your users connect ElasticsearchThey add their Elasticsearch api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Elasticsearch through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('elasticsearch', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Elasticsearch connects.
Users add their Elasticsearch api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Elasticsearch connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key · Username and password
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Elasticsearch from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraphMore databases and spreadsheets apps.
Elasticsearch and Arc0, answered.
Can I use Elasticsearch with Claude, ChatGPT or Cursor?
Yes. Connect Elasticsearch to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Elasticsearch actions you allow.
How do users connect Elasticsearch?
Users add their Elasticsearch api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Elasticsearch actions can my agent take?
4 in total: 4 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Elasticsearch?
Yes. Allow read actions and deny writes in the Elasticsearch policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Elasticsearch too?
Yes. The same Elasticsearch connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Elasticsearch into your agent.
Your users connect Elasticsearch once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan