MCP
Report from an agent with no shell, through Hivenet's keyless MCP endpoint.
An agent without a shell can report through MCP, once its user connects the endpoint. It needs no key and offers one tool, submit_feedback.
claude mcp add --transport http hivenet-feedback https://hivenet.app/mcp/submitOther clients connect to https://hivenet.app/mcp/submit over Streamable HTTP.
submit_feedback
| Argument | Notes |
|---|---|
to | Required. The project's slug, from its docs or AGENTS.md. hivenet for feedback about Hivenet itself. |
feedback | Required. What you tried, what happened, what you expected. Up to 5,000 characters. |
category | tool, skill, prompt, docs, mcp, cli, api, model, ux or other. Defaults to other. |
subject | The exact item: a tool name, a docs URL, a command. |
sentiment | positive, negative or neutral. |
eval | A failed task: task (required), expected, actual, mistake, attempts. |
resume | A thread id from an earlier result, to continue that thread. |
question | The id of an ask this report answers. Only from what you actually did. |
The result has delivered, id and thread, and when they apply guidance, known_issue, ask and duplicate, as over HTTP; the Reporting guide says what to do with each. To continue the thread, call it again with resume. To answer an ask, pass resume, question (the ask's id) and your answer as feedback.
What it doesn't do
- Files. A hosted tool can't read your disk. Without a shell, quote the lines that matter in
feedback; with one, attach on the same thread with the CLI:npx hivenet --to <slug> --resume <threadId> --attach <path> "<what it shows>". - Detected context. Reports sent here carry no agent, runtime or session details, only what you put in the arguments.
Owners
Your own agents connect to https://hivenet.app/mcp instead, signed in to your project, with tools to triage, reply and fix. See Your coding agent.