Which leaked secrets are still valid, and which repositories are at risk?
GitGuardian finds secrets leaked into code, and Memtro reads its incidents: detector, severity, whether the secret is still valid, status, assignee, where it was found and the notes on it. It also reads monitored repositories with their health, and workspace members. The secret itself, the commit author and the matched text are never returned. When asked and once an administrator has granted the action by name, it can add notes, resolve, ignore or reopen incidents, assign them, change severity, re-check presence and start scans of named sources. An assignee may be emailed. Deleting a note is permanent.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right GitGuardian tool, reads what it needs, and answers with the source cited.
These tools change something in GitGuardian. 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 GitGuardian, choosing the same kinds; the tab shows GitGuardian's own steps. Each event can start a job, with the event as its input. GitGuardian signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce GitGuardian 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.
GitGuardian + MemtroWhich leaked secrets are still valid?
Which repositories are at risk?
Where was the latest AWS key incident found?
Which open incidents are assigned to Sarah?
Resolve the Slack token incident, the token was revoked this morning.
Sarah Chen, security lead at Northwind, asked which leaked secrets were still valid. Memtro listed the open incidents with a valid secret by severity and named each assignee from the member list. It showed the repository and file path where each was found.
Sarah told Memtro the leaked Slack token had been revoked and asked it to close the incident. Memtro added her note saying so, then resolved the incident recording that the secret was revoked. It left the open incidents everyone in the workspace sees.
The teams that lean on GitGuardian most, a question each of them asks, and what they connect beside it.
A record in GitGuardian 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.
UptimeRobot
Honeycomb
Cronitor
FireHydrant
StatusCake
GlitchTip
GLPI
Langfuse
LibreNMS
NetBox
Snipe-IT
Woodpecker CI
Zabbix
LangSmith
Helicone
GrowthBook
Drata
Intruder
Secureframe
ilert
JumpCloud
ConfigCat
Split
Aikido Security
Astronomer
Comet Opik
CrowdStrike Falcon
Detectify
Domotz
LambdaTest
LangWatch
LlamaCloud
Logz.io
Lunary
NinjaOne
Northflank
Portkey
PromptLayer
PRTG Network Monitor
Raygun
Retell AI
Runpod
Shodan
Spike.sh
Squadcast
Tenable
UpGuard
Uptime.com
Vanta
Zenduty
Cortex
WorkOS
Kandji
Automox
Huntress
SimpleMDM
Healthchecks.io
Rapid7 InsightVM
ZenhubIn the GitGuardian dashboard, sign in as a member who can see the incidents you will ask about. Open API → Personal access tokens → Create token.
Name it Memtro, choose an expiry and tick incidents:read, sources:read and members:read. Add incidents:write only if Memtro should change incidents or their notes, and sources:scan only if it should start scans. Copy the token, which is shown once.
In Memtro, open Connections → GitGuardian, paste it into Personal access token and set Region to eu if your dashboard is on eu1.
Ask: which leaked secrets are still valid?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The GitGuardian tools are the same everywhere.
Only when you ask, and only what it has been granted: add a note to a secret incident; resolve a secret incident (saying whether the secret was revoked), ignore it with a reason, or reopen it; assign a secret incident to a workspace member, or unassign it; change a secret incident's severity; re-check whether an incident's secret is still present in its sources; edit or delete a note this connection wrote on an incident; start historical scans of named sources. 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.
Personal access token. In the GitGuardian dashboard, sign in as a member who can see the incidents you will ask about. Open API → Personal access tokens → Create token.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in GitGuardian, choosing the same kinds; the tab shows GitGuardian'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
