Credentials. The agent gets the same tools as you over OAuth, so limit it to the workspace it needs and revoke access when it is no longer used.
Who it is forA developer who wants an agent to refresh a runbook or API page after a deploy, without copy-pasting between tools.
The problemAgents cannot see the charts and explanations a team keeps in a wiki, so their suggested changes go stale or are made by hand.
The outcomeThe agent edits the page through Oxynote's tools, and the change waits in a draft for a human to review.
What you need first
- Docker installed, with port 8080 free on the host
- A Prometheus server or a PostgreSQL, MySQL or MariaDB database to query for live metric blocks
- The default login from the README ([email protected]) changed before any real data goes in
- For agent access: Claude Code or Codex installed, able to use MCP over OAuth
Steps
- Run
docker run -d --name oxynote -p 8080:8080 -v oxynote_data:/oxynote/data ghcr.io/oxynote/oxynote:latest(join the lines into one command). (inferred, check the README) - Open http://localhost:8080, log in, and choose the model provider you want Rubber Duck to use.
- Add Oxynote as an MCP server in Claude Code or Codex and complete the OAuth sign-in. (inferred, check the README)
- Ask the agent to edit a named page, then open the resulting draft in Oxynote.
- Approve the draft only after you have read the diff.
Prompt for your agent
Using the oxynote/oxynote MCP server at <oxynote-url>, update the page <page-title> to reflect <change-description>. Expected output: the draft link and a short list of the blocks changed. Verify that the change appears as a draft and that main is untouched.
Caveat. The README says MCP clients get the same tools over OAuth but does not list the exact MCP setup steps, so follow the current docs for each agent.
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page