Checking an import
Tom Reilly, ML engineer at Acme Ltd, asked whether the overnight bulk import had finished. Memtro read the import's status and records imported, then the index's record count per namespace.
Pinecone + Memtro
How many records are in each Pinecone index, and when was it last backed up?
Pinecone stores your vectors, and Memtro reads the project for you. It reads indexes with their type, region, size, model and deletion protection, and record counts per namespace. It also reads namespaces, backups, restore jobs and bulk imports. When asked and granted, it can configure or back up an index, restore a backup, or delete an index or backup. It can also create or delete a namespace, delete records by id, update a record's metadata and cancel an import. A key belongs to one project, so connect each separately.
In Memtro
What you can do with Pinecone in Memtro
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Pinecone tool, reads what it needs, and answers with the source cited.
What it does
- 01Reads indexes with serverless or pod type, region, dimension, metric, embedding model, deletion protection and tags.
- 02Reads record counts per namespace, namespaces with their metadata fields, and how full a pod index is.
- 03Reads backups, restore jobs and bulk imports with their status and progress.
- 04When asked and granted, configures an index's replicas, pod size, deletion protection or tags, which can change its cost.
- 05When asked and granted, backs up an index, restores a backup into a new billed index, or deletes an index or backup permanently.
- 06When asked and granted, creates or deletes a namespace, deletes records by id, updates a record's metadata, or cancels an import.
Acts when asked
When you ask it to
These tools change something in Pinecone. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
- 01Configure an index: replicas, pod size, deletion protection or tags
- 02Back up an index
- 03Restore a backup into a new index
- 04Delete an index
- 05Delete a backup
- 06Create a namespace in an index
- 07Delete a namespace and all its records
- 08Delete records by id
- 09Update a record's metadata
- 10Cancel a bulk import
In practice
Ask it like you would a colleague
Once Pinecone 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.
Pinecone + Memtro
How many records does each index hold?
Which namespaces are largest in the support-docs index?
When was the products index last backed up?
Did last night's bulk import finish, and were there errors?
Turn on deletion protection for the production index.
Backing up before a change
Priya Sharma, platform lead at Northwind, asked Memtro to back up the search index before a re-embedding run. Memtro took the backup, and its status showed in Pinecone for the team.
Teams
Where it fits
The teams that lean on Pinecone 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 Pinecone 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.
- AnalyticsPinecone with Google Analytics 4Ask your traffic questions in plain English and get the numbers back.
- AnalyticsPinecone with Plausible AnalyticsAsk about your website traffic in plain English.
- AnalyticsPinecone with UmamiAsk about your website traffic in plain English, without sending anybody to a dashboard.
- Finance and commercePinecone with XeroInvoices, bills, contacts and reports, answered in plain English with figures cited to Xero.
- Finance and commercePinecone with StripeCustomers, charges, invoices and subscriptions through a restricted key.
- Finance and commercePinecone with FellohBookings, payments, refunds, chargebacks, supplier payments and payouts from the travel payments platform.
- Work managementPinecone with JiraJQL search, issue details and projects from Jira Cloud.
- Work managementPinecone with Clio ManageAsk the matter: its client, its fee earner, the time on it and what is still unbilled.
- Work managementPinecone 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
- Elasticsearch
- 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- PlanetScale
- Quickbase
Secoda
Softr
Teable- Turso
- Upstash
Vectara- Xata
- Zilliz Cloud
Setup
How to connect
Connect withAPI key
- 1
In Pinecone, open your project, then API keys, and create a key. A read-only role is enough for reading, while actions need one that can manage indexes and write data.
- 2
In Memtro, open Connections → Pinecone and paste the API key. The key is shown once.
- 3
An administrator grants the index, backup and record actions by name only to the engineers who may use them. Deletes cannot be undone.
- 4
Ask how many records each index holds.
Also works from
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Pinecone tools are the same everywhere.
FAQ
Questions
Can Memtro change anything in Pinecone?+
Only when you ask, and only what it has been granted: configure an index: replicas, pod size, deletion protection or tags; back up an index; restore a backup into a new index; delete an index; delete a backup; create a namespace in an index; delete a namespace and all its records; delete records by id; update a record's metadata; cancel a bulk import. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
Who can use a Pinecone 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 Pinecone 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 Pinecone?+
API key. In Pinecone, open your project, then API keys, and create a key. A read-only role is enough for reading, while actions need one that can manage indexes and write data.
Connect Pinecone in a few minutes
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.