During the incident
An engineer asks what the payments service logged in the last 15 minutes. Memtro searches logs-* for the service and level, sorts by timestamp and returns the lines with the query it used.
Elasticsearch + Memtro
Search, count and aggregate your Elasticsearch indices in plain English, nothing written.
Connect Elasticsearch, or OpenSearch, with its endpoint and an API key or a username and password, and Memtro can check cluster health, list indices with document counts and sizes, read an index's field mapping, search by Lucene query string or query DSL, count matches exactly, and aggregate by top values, time bucket or statistics. It only reads: no document is written or deleted and no setting is changed.
In Memtro
What you can do with Elasticsearch in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Elasticsearch tool, reads what it needs, and answers with the source cited.
Reads
- 01Cluster name, version, green, yellow or red status, node and shard counts
- 02Indices by pattern with document counts, sizes and shards; system indices hidden unless asked for
- 03An index's fields flattened to dotted names with their types, so a query uses the right ones
- 04Search with a Lucene query string or raw query DSL, sorted, at most 100 hits a call
- 05Exact counts of matching documents, even past the 10,000 a search total stops at
- 06Terms, date-histogram and stats aggregations: top hosts, errors per hour, average response time
In practice
Ask it like you would a colleague
Once Elasticsearch is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
Elasticsearch + Memtro
How many documents in logs-* have status:500 in the last hour?
What are the top 10 hosts by error count today?
Show me errors per hour for the last 24 hours in logs-nginx-*
Which indices are over 50 GB, and is the cluster green?
Find the last 20 log lines mentioning 'connection refused' from payments-api
Counting, not scrolling
Someone wants to know how many orders landed in the orders index last month by country. Memtro runs a terms aggregation on country.keyword with a date filter and returns the buckets, not ten thousand hits.
Teams
Where it fits
The teams that lean on Elasticsearch most, a question each of them asks, and what they connect beside it.
- Data and analyticsQuestions answered from the warehouse, with the SQL shownAnalyst, Data engineer, Anybody with a question, Head of data“Revenue by segment for Q3 from the warehouse, with the SQL you used”Used alongside Postgres, Stripe, Slack, Google Drive, Snowflake and 3 more.
- EngineeringKeep decisions from evaporatingEngineer, Tech lead, On call, New joiner“Who owns the billing migration, and what did we decide about retries?”Used alongside GitHub, Linear, Jira, Confluence, Slack and 5 more.
- FinanceAsk the ledger questions in plain EnglishFinance lead, Credit control, Management accountant, Founder or CFO“Which invoices over £5k are more than 30 days overdue?”Used alongside Xero, Stripe, Postgres, HubSpot, QuickBooks Online and 10 more.
Better together
Works with
A record in Elasticsearch is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
- AnalyticsElasticsearch with Google Analytics 4Ask your traffic questions in plain English and get the numbers back.
- AnalyticsElasticsearch with Plausible AnalyticsAsk about your website traffic in plain English.
- AnalyticsElasticsearch with UmamiAsk about your website traffic in plain English, without sending anybody to a dashboard.
- Finance and commerceElasticsearch with XeroInvoices, bills, contacts and reports, answered in plain English with figures cited to Xero.
- Finance and commerceElasticsearch with StripeCustomers, charges, invoices and subscriptions through a restricted key.
- Finance and commerceElasticsearch with FellohBookings, payments, refunds, chargebacks, supplier payments and payouts from the travel payments platform.
- Work managementElasticsearch with JiraJQL search, issue details and projects from Jira Cloud.
- Work managementElasticsearch with Clio ManageAsk the matter: its client, its fee earner, the time on it and what is still unbilled.
- Work managementElasticsearch with LinearIssues, projects and teams, synced hourly into memory.
Also in Databases and warehouses
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
- Postgres
- MySQL and MariaDB
- SQL Server
- BigQuery
- Snowflake
- AWS Athena
- MongoDB
- ClickHouse
- Amazon Redshift
- Databricks
- dbt Cloud
- Fivetran
- Neon
- Appwrite
Grist- Hasura
- Meilisearch
NocoDB- Qdrant
Typesense
Weaviate
Tinybird
Hightouch
Census- Airbyte
- Budibase
- CockroachDB Cloud
- Cube Cloud
- DataHub
kintone
Monte Carlo
OpenMetadata- Pinecone
- PlanetScale
- Quickbase
Secoda
Softr
Teable- Turso
- Upstash
Vectara- Xata
- Zilliz Cloud
Setup
How to connect
Connect withAPI key or username and password
- 1
In Kibana open Stack Management → API keys → Create API key with read and view_index_metadata on the indices Memtro should see, and monitor on the cluster for health and sizes
- 2
Copy the key in its encoded form; it is shown once. A username and password work instead
- 3
Paste it with the Elasticsearch endpoint (not Kibana's, with the port if not 443) into Connections → Elasticsearch in Memtro and connect
- 4
Ask which index grew most this week, or how many 500s the API logged today
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Elasticsearch tools are the same everywhere.
FAQ
Questions
Can Memtro change anything in Elasticsearch?+
Not yet. Today every Elasticsearch tool reads, searches or lists. When the connector gains actions, each is marked, granted by name per team and used only when a person asks for exactly that, so nothing is created, sent, updated or deleted until you say so.
Who can use a Elasticsearch connection?+
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Does Memtro store my Elasticsearch data?+
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
How do I connect Elasticsearch?+
API key or username and password. In Kibana open Stack Management → API keys → Create API key with read and view_index_metadata on the indices Memtro should see, and monitor on the cluster for health and sizes.
Connect Elasticsearch in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.