Elasticsearch
Search, index, and manage documents and indices on any Elasticsearch cluster.
About
Elasticsearch ships in the w6w first-party pack. It declares 9 actions, 3 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.elastic- Version
- 0.1.2
- Author
- w6w
- Licence
- MIT
- Categories
- Search
Overview
Elasticsearch is a search and analytics engine that speaks plain HTTP for every operation, and this app exposes that directly: search with the full Query DSL, index, fetch, update and delete individual documents, and create, delete, list and inspect indices and their mappings.
Because an Elasticsearch cluster can live anywhere — a hosted deployment, a customer’s own VPC, an on-prem box — this app connects to whichever cluster a workflow’s credentials point at rather than a single fixed vendor host, so it works the same way against Elastic Cloud, a self-managed cluster, or another cloud provider’s managed Elasticsearch.
Search passes a query straight through in Elasticsearch’s own DSL, which means anything the engine can express — full-text search, filters, aggregations — is available rather than a narrowed subset. Document actions cover indexing with or without an explicit id, partial updates that merge into an existing document, and deletion; index actions cover creation with optional mappings and settings, deletion, listing and reading a mapping back.
Build with Elasticsearch
Three routes to the same 9 actions. The Workflow tab is generated from Elasticsearch's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
Update Document
document-update Partially update a document by merging fields into its existing `_source`.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Elasticsearch's real ids.
{
"manifestVersion": "2",
"name": "elastic-example",
"steps": [
{
"id": "document-get",
"uses": {
"app": "io.w6w.elastic",
"action": "document-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"index": "<index>",
"id": "<id>"
}
}
]
}Here are some of the things you can do
-
Get Document
readdocument-get -
Index Document
performdocument-index -
Update Document
performdocument-update -
Create Index
performindex-create -
List Indices
readindex-list
+4 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Elasticsearch, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Elasticsearch. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "document-index",
payload: {
index: "<value>",
// id: "<value>",
document: "<value>",
// refresh: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action document-index --payload '{"index":"<value>","document":"<value>"}'Give an AI agent Elasticsearch — without giving it Elasticsearch's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.elastic#document-get",
"input": {
"index": "<index>",
"id": "<id>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Elasticsearch connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
A tool surface scoped to the caller
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
A durable workflow in one call
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Health-aware discovery
Elasticsearch's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Elasticsearch itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
Elasticsearch declares its own checks, so its health is a property of the app rather than something the host guesses at.
Elasticsearch platform status
API quota headroom
Cluster reachable
Unauthenticated `GET /` against this connection's endpoint. A 401 counts as reachable — it proves a live, security-enabled Elasticsearch cluster answered.