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

UpGuard + Memtro

Which of our vendors have the lowest UpGuard scores, and what risks changed this month?

UpGuard connects Memtro to UpGuard CyberRisk. It reads your own security score and active risks, then the vendors you monitor with scores, tiers, labels and assessment status. For a vendor it reads active risks, how they changed between two dates, and its security questionnaires. It also reads Threat Monitoring findings. When asked and granted, it can start or stop monitoring a vendor, set its labels, tier or attributes, send a questionnaire, comment on or move a questionnaire, and comment on, assign, close, reopen or request remediation of a threat. Threat post text is never returned.

Connect UpGuardStart for freeReference
In Memtro

What you can do with UpGuard in Memtro

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

What it does

  1. 01Your organisation's security score, the score in each category, and its active risks with remediation advice.
  2. 02Monitored vendors with score, tier, labels, lifecycle stage and assessment status, and one vendor's risk counts and domains.
  3. 03A vendor's active risks, what changed between two dates, and its questionnaires with status and due dates.
  4. 04Threat Monitoring findings with severity, status, source, dates and investigator, never the post text.
  5. 05When asked and granted, starts or stops monitoring a vendor, which uses or frees a licensed slot, and sets its labels, tier or attributes. Nobody is notified.
  6. 06When asked and granted, sends a questionnaire, which UpGuard emails to people at the vendor, moves or comments on a questionnaire, and works threats. A remediation request emails the person named.

Acts when asked

When you ask it to

These tools change something in UpGuard. 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. 01Start monitoring a vendor (uses a licensed vendor slot)
  2. 02Stop monitoring a vendor
  3. 03Replace a vendor's labels
  4. 04Set or clear a vendor's tier
  5. 05Set or remove a vendor's attributes
  6. 06Send a security questionnaire to named people at a vendor
  7. 07Comment on a vendor questionnaire
  8. 08Change a questionnaire's review status
  9. 09Comment on a threat
  10. 10Assign a threat's investigator
  11. 11Close a threat with a reason
  12. 12Reopen a closed threat
  13. 13Request remediation of a threat from a named person
In practice

Ask it like you would a colleague

Once UpGuard 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.

UpGuard logoUpGuard + Memtro

  • Which monitored vendors have the lowest scores?

  • What risks did our payroll vendor introduce or resolve this month?

  • Which vendor questionnaires are past their due date?

  • What are our own critical risks right now?

  • Set the payroll vendor to tier 1.

01

Vendor risk before renewal

Tom Reilly, procurement lead at BigCo, asked how a supplier's security had changed before its renewal. Memtro read the vendor's score and active risks, then the risks introduced and resolved over the last 30 days. He raised the new ones on the renewal call.

02

Sending a questionnaire

Sarah Chen, security analyst at Acme Ltd, asked Memtro to send the security questionnaire to two contacts at a newly monitored supplier. With the action granted, Memtro sent it, and UpGuard emailed each of them an invitation. The questionnaire then showed as sent in the vendor's list.

Teams

Where it fits

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

Better together

Works with

A record in UpGuard 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 UpGuard CyberRisk, open Account Settings, then API keys, and create a key. Give it Platform, VendorRisk, BreachRisk and ReadWrite, and leave out IdentityBreaches, UserRisk and Admin.

  2. 2

    In Memtro, open Connections → UpGuard and paste the API key.

  3. 3

    An administrator grants the vendor, questionnaire and threat actions by name to the teams that may use them, since a questionnaire reaches people outside the company.

  4. 4

    Ask which monitored vendors have the lowest scores.

Also works from

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

Set it up as an MCP serverClients and agents
FAQ

Questions

Can Memtro change anything in UpGuard?+

Only when you ask, and only what it has been granted: start monitoring a vendor (uses a licensed vendor slot); stop monitoring a vendor; replace a vendor's labels; set or clear a vendor's tier; set or remove a vendor's attributes; send a security questionnaire to named people at a vendor; comment on a vendor questionnaire; change a questionnaire's review status; comment on a threat; assign a threat's investigator; close a threat with a reason; reopen a closed threat; request remediation of a threat from a named person. 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 UpGuard 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 UpGuard 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 UpGuard?+

API key. In UpGuard CyberRisk, open Account Settings, then API keys, and create a key. Give it Platform, VendorRisk, BreachRisk and ReadWrite, and leave out IdentityBreaches, UserRisk and Admin.

Connect UpGuard 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