Cost control: a monthly token allowance for each modelSee how it works
memtro
Start for free
LlamaCloud logo

LlamaCloud + Memtro

How many credits did parsing use this month, and which jobs failed?

LlamaCloud connects Memtro to your LlamaParse document processing project. It reads parse, extract and classify jobs with status, tier, errors and credits spent. It also reads managed indexes and pipelines with their sync state, files by type and expiry, and credit usage by day, event type or tier. When asked and granted, it can parse, extract from or classify a document, cancel or delete jobs, sync an index and delete indexes and files. LlamaCloud can also tell Memtro as jobs finish or fail, and a job can start on it. Parsed text and file names are never returned.

Connect LlamaCloudStart for freeReference
In Memtro

What you can do with LlamaCloud in Memtro

Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right LlamaCloud tool, reads what it needs, and answers with the source cited.

What it does

  1. 01Parse, extract and classify jobs with status, tier, error and credits, and a classification's document type with confidence.
  2. 02Managed indexes with when they were last synced, and retrieval pipelines with their ingestion status.
  3. 03Files by type, purpose and expiry, and credits spent by day, event type, tier or project.
  4. 04When asked and granted, parses a document from an uploaded file or public URL, extracts structured fields or classifies it. Each spends credits.
  5. 05When asked and granted, cancels a running job, deletes a finished one, syncs an index or cancels its sync, and permanently deletes an index or a file.
  6. 06With events on, a parse job finishing, an extract job failing or a classify job finishing in LlamaCloud can start a job.

Acts when asked

When you ask it to

These tools change something in LlamaCloud. 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.

  1. 01Parse a document from an uploaded file or public URL (spends credits per page)
  2. 02Extract structured fields from a document (spends credits per page)
  3. 03Classify a document against rules (spends credits)
  4. 04Cancel a running parse, extract or classify job
  5. 05Delete a finished job and its results
  6. 06Sync an index, re-parsing changed files (spends credits)
  7. 07Cancel an index's running sync
  8. 08Delete an index
  9. 09Delete a file

Events

When it happens

Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in LlamaCloud, choosing the same kinds; the tab shows LlamaCloud's own steps. Each event can start a job, with the event as its input. LlamaCloud signs every delivery, and one whose signature does not check out is refused before it is read.

Events and webhooks
  • 01A parse job finished
  • 02A parse job finished with warnings
  • 03A parse job failed
  • 04A parse job was cancelled
  • 05An extract job finished
  • 06An extract job finished with warnings
  • 07An extract job failed
  • 08An extract job was cancelled
  • 09A classify job finished
  • 10A classify job finished with warnings
  • 11A classify job failed
  • 12A classify job was cancelled
  • 13A split job finished
  • 14A split job failed
  • 15A split job was cancelled
  • 16A verify job finished
  • 17A verify job failed
  • 18A verify job was cancelled
  • 19A batch finished (files may still have failed)
  • 20A batch failed
In practice

Ask it like you would a colleague

Once LlamaCloud 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.

LlamaCloud logoLlamaCloud + Memtro

  • How many credits did parsing use this month?

  • Which parse jobs failed this week, and why?

  • When was the contracts index last synced?

  • What document types did yesterday's classify jobs find?

  • Sync the contracts index now.

01

Credit spend explained

Dan Fletcher, engineering lead at Acme Ltd, asked how many credits parsing used this month. Memtro read the usage by day and tier. He saw where the spend went and took it to the budget meeting.

02

Failed parse starts a job

When a parse job failed at Northwind, LlamaCloud told Memtro and a job started. It read the job's status, tier and error and posted the cause for Sarah Chen, the data engineer. She fixed the source document and asked Memtro to parse it again.

Teams

Where it fits

The teams that lean on LlamaCloud most, a question each of them asks, and what they connect beside it.

Better together

Works with

A record in LlamaCloud 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.

Also in Engineering and operations

Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.

Setup

How to connect

Connect withAPI key
  1. 1

    In LlamaCloud, open the project Memtro should read, then API Key → Generate New Key. Copy it at once, since it is not shown again.

  2. 2

    In Memtro, open Connections → LlamaCloud and paste the API key. Set the Region to eu if the account is on the EU host.

  3. 3

    An administrator grants the actions by name, such as Parse a document, to the teams that may use them. Events are turned on from the connection's Events tab, and the address is then saved as a webhook configuration your code passes when it creates jobs.

  4. 4

    Ask "How many credits did parsing use this month?"

Also works from

Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The LlamaCloud tools are the same everywhere.

Set it up as an MCP serverClients and agents
FAQ

Questions

Can Memtro change anything in LlamaCloud?+

Only when you ask, and only what it has been granted: parse a document from an uploaded file or public URL (spends credits per page); extract structured fields from a document (spends credits per page); classify a document against rules (spends credits); cancel a running parse, extract or classify job; delete a finished job and its results; sync an index, re-parsing changed files (spends credits); cancel an index's running sync; delete an index; delete a file. 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 LlamaCloud 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 LlamaCloud 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 LlamaCloud?+

API key. In LlamaCloud, open the project Memtro should read, then API Key → Generate New Key. Copy it at once, since it is not shown again.

Can LlamaCloud start a job?+

Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in LlamaCloud, choosing the same kinds; the tab shows LlamaCloud's own steps. A job set to start "When an event arrives" then runs once for each matching event, with the event as its input. The run treats the event as outside data, never as instructions, and anything the run remembers is kept as unverified.

Connect LlamaCloud in a few minutes

Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.

Start for freePricing

Where agents remember your company

Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.

Start for freeGetting started

7-day free trial · card on file, nothing charged until it ends · cancel any time