The weekly Claude bill
Priya Sharma, CTO at BigCo, asked what the team spent on Claude last week and which workspace cost most. Memtro read the daily cost report per workspace and line item and named the workspace with the highest total.
What did we spend on the Claude API this week, and which workspace uses most tokens?
This connects your Anthropic organisation's Admin API for usage and cost. It never calls a model. Memtro reads daily cost in USD by workspace and line item, token usage by model, workspace and API key, workspaces, members and the names of API keys, never a key value or hint. When asked and once an administrator has granted the action by name, it can invite people by email, change or remove members and roles, and create or rename workspaces. Archiving a workspace is permanent and stops its API keys working. Claude Enterprise on claude.ai is not covered.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Anthropic (usage and cost) tool, reads what it needs, and answers with the source cited.
These tools change something in Anthropic (usage and cost). 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.
Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Anthropic (usage and cost), choosing the same kinds; the tab shows Anthropic (usage and cost)'s own steps. Each event can start a job, with the event as its input. Anthropic (usage and cost) signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Anthropic (usage and cost) 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.
What did we spend on Claude last week?
Which workspace used the most tokens in the last 30 days?
How many cache reads did each model have in the last 7 days?
Which keys are still active in the prod workspace?
Invite dan@acme.com to the organisation as a developer.
Priya Sharma, CTO at BigCo, asked what the team spent on Claude last week and which workspace cost most. Memtro read the daily cost report per workspace and line item and named the workspace with the highest total.
Dan Fletcher, security lead at Acme Ltd, asked Memtro to invite Maya Okafor as a developer. Memtro sent the invite with that role, and Anthropic emailed Maya a link. Once she accepted, Dan asked for her to be added to the prod workspace as a developer, and Memtro did that too.
The teams that lean on Anthropic (usage and cost) most, a question each of them asks, and what they connect beside it.
A record in Anthropic (usage and cost) 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.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
In Anthropic, open platform.claude.com → Settings → Admin keys. An ordinary inference key (sk-ant-api…) will not work here.
Create an admin key named for Memtro, with an expiry, so you can revoke it. Admin keys have no scopes, so Memtro changes members, invites or workspaces only when an administrator grants that. Copy it, as it is shown once.
In Memtro, open Connections → Anthropic (usage and cost) and paste it into Admin API key. Memtro never calls a model with it.
Ask: "What did we spend on Claude last week?"
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Anthropic (usage and cost) tools are the same everywhere.
Only when you ask, and only what it has been granted: invite someone to the Anthropic organisation by email with a chosen role (Anthropic emails them); cancel a pending Anthropic organisation invite; change a member's Anthropic organisation role; remove a member from the Anthropic organisation; create an Anthropic workspace; rename or recolour an Anthropic workspace; archive an Anthropic workspace permanently: its API keys stop working; add an organisation member to an Anthropic workspace with a chosen role; change a member's role in an Anthropic workspace; remove a member from an Anthropic workspace. 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.
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.
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.
Admin API key. In Anthropic, open platform.claude.com → Settings → Admin keys. An ordinary inference key (sk-ant-api…) will not work here.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in Anthropic (usage and cost), choosing the same kinds; the tab shows Anthropic (usage and cost)'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.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time