HackerOne MCP server
HackerOne in any MCP client, through Memtro: HackerOne does not publish this server. Memtro's HackerOne connector reads HackerOne through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.
What the model can do
HackerOne bug bounty and vulnerability disclosure programmes: reports by programme, state, severity, reporter, assignee and date, a report's write-up, triage details and activity timeline with comment text, the programmes the token belongs to with their groups, members by name and username, in-scope assets and weaknesses. When asked, can add an internal comment, post a public comment to the hacker, assign a report, change its state, set its severity, replace its tags, add a summary, change its title, set the issue tracker reference and suggest a bounty internally.
Reads
hackerone_list_programsThe HackerOne programmes this API token belongs to: numeric id and handle.hackerone_get_programOne HackerOne programme: handle, organisation, accepted severity calculation methods, its groups (id, name, permissions) and members (user id, name…hackerone_list_reportsHackerOne vulnerability reports in one or more programmes: title, state, severity, reporter's username, assignee (name and username), weakness…hackerone_get_reportOne HackerOne report: the vulnerability write-up (up to 6000 characters), its triage details (state, severity and score, programme…hackerone_list_activitiesActivity across a HackerOne programme, or on one report, by update time: what happened (comment, state change, bounty, assignment…), on which report…hackerone_list_scopesA HackerOne programme's structured scope: each asset (identifier and type), its maximum severity…hackerone_list_weaknessesThe weakness types a HackerOne programme accepts (name and CWE id), for reading report weaknesses or filtering by one.
Acts, when you ask
These change something in HackerOne. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.
hackerone_add_internal_commentAdd an internal comment to a HackerOne report.hackerone_post_public_commentPost a PUBLIC comment on a HackerOne report.hackerone_assign_reportAssign a HackerOne report to a programme user or group (ids from hackerone_get_program), or clear the assignee with assignee_type nobody.hackerone_change_stateChange a HackerOne report's state (e.g. triaged, needs-more-info, resolved, duplicate, informative, not-applicable, spam).hackerone_set_severitySet a HackerOne report's severity rating (none, low, medium, high, critical).hackerone_replace_tagsSet a HackerOne report's tags.hackerone_add_summaryAdd the team's summary to a HackerOne report.hackerone_update_titleChange a HackerOne report's title.hackerone_set_issue_referenceSet the issue tracker reference on a HackerOne report (e.g. a Jira key), replacing the current one; earlier references stay in the timeline.hackerone_suggest_bountySuggest a bounty on a HackerOne report for the team to decide on.
Connect it
First connect HackerOne on Dashboard → Connections, then add Memtro to your client once. The HackerOne tools appear alongside the tools of everything else you have connected; nothing is configured per connector.
Claude Code
The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.
claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...Cursor
Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.
{
"mcpServers": {
"memtro": {
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Claude Desktop
Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…
OpenCode
A remote server in opencode.json.
{
"mcp": {
"memtro": {
"type": "remote",
"url": "https://platform.memtro.com/api/mcp",
"headers": {
"Authorization": "Bearer sk-memtro-..."
}
}
}
}Pi
One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.
Any other client
Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.
Who may use it
The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared HackerOne connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.
Ask it like this
- › 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
Questions
- Is this an official HackerOne MCP server?
- No. It is Memtro's MCP server with Memtro's HackerOne connector behind it: the connector reads HackerOne through its API with the credentials you connect on Dashboard → Connections, and HackerOne publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
- What does it cost?
- Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
- Can it change anything in HackerOne?
- 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. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
- Which clients work?
- Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.