Monday triage
Maya Okafor, security engineer at Acme Ltd, asked which new reports had come in over the weekend. Memtro listed them with severity, asset and weakness, and the first lines of each write-up.
Which vulnerability reports are still untriaged, and how severe are they?
HackerOne connects Memtro to your bug bounty and vulnerability disclosure programmes. It reads reports by programme, state, severity, reporter, assignee and date, a report's write-up, triage details and activity timeline, programme members, in-scope assets and weaknesses. When asked, and once an administrator has granted the action by name, it can add an internal comment, post a public comment the hacker sees, assign a report, change its state or severity, replace its tags, add a summary, change its title, set an issue reference and suggest a bounty internally. Attachments and bounty amounts are never returned.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right HackerOne tool, reads what it needs, and answers with the source cited.
These tools change something in HackerOne. 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 HackerOne, choosing the same kinds; the tab shows HackerOne's own steps. Each event can start a job, with the event as its input. HackerOne signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce HackerOne 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.
Which reports are waiting for triage?
What critical reports were submitted this month?
What happened on our programme this week?
Which assets are eligible for bounty?
Assign report 2481234 to the platform team
Maya Okafor, security engineer at Acme Ltd, asked which new reports had come in over the weekend. Memtro listed them with severity, asset and weakness, and the first lines of each write-up.
Dan Fletcher, security lead at Northwind, asked Memtro to assign a high severity report to the platform team and set its Jira reference. Memtro assigned it in HackerOne, which notified the team's subscribers, and set the issue tracker reference.
The teams that lean on HackerOne most, a question each of them asks, and what they connect beside it.
A record in HackerOne 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 HackerOne, open Organization settings → API tokens and create a token named Memtro. Only organisation admins can create one.
Give it the groups for the programmes Memtro should see. Report Management is needed for comments to hackers, assignment, state and the other report changes.
In Memtro, open Connections → HackerOne and enter the API token identifier, which is not an email address, and the API token value, shown once.
Ask your first question: which reports are waiting for triage?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The HackerOne tools are the same everywhere.
Only when you ask, and only what it has been granted: add an internal comment to a report (programme members only); post a public comment on a report (the hacker who reported it is notified); assign a report to a user or group, or clear the assignee; change a report's state (visible to the hacker; resolved credits them, N/A, informative and spam deduct reputation); set a report's severity rating; replace a report's tags; add the team's summary to a report; change a report's title; set a report's issue tracker reference; suggest a bounty on a report (internal, moves no money). 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. An hourly sync anchors recently changed HackerOne records into memory as entities.
API token identifier and API token value. In HackerOne, open Organization settings → API tokens and create a token named Memtro. Only organisation admins can create one.
Yes. Turn events on in the connection's Events tab on the Connections page, then add the address it shows as a webhook in HackerOne, choosing the same kinds; the tab shows HackerOne'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