Credentials. Logged-in sites need your browser session imported into the local vault, so the agent acts with your account until you deny writes.
Who it is forA content writer or marketer who wants an AI assistant to draft posts on a site they already use.
The problemLetting an agent write to a live account can post, edit, or delete content you did not intend to change.
The outcomeA draft created on the site only after you approved write actions for that CLI.
What you need first
- A Hycli release package for Windows, macOS, or Linux (Rust and Node.js are not needed to run it)
- An AI connection: an OpenAI, Anthropic Claude, xAI, or Z.ai API key, or a local ChatGPT Codex login
- The URL of the target website and a short goal for it
- An MCP client such as Claude Code, Cursor, or Codex, if your agent will call Hycli
Steps
- Add
"command": "hycli", "args": ["mcp"]to your MCP client settings for Claude Code, Cursor, or Codex. - Ask your agent: "Use Hycli to prepare
https://..., show me what actions are available, and draft a new post." - When the agent asks, approve writes once for that CLI, which runs
hycli writes your-website allow. - Run
hycli your-website create-draft --title "Hello from Hycli" --body "Automated from my terminal."to confirm the draft path works. - Run
hycli writes your-website denywhen you no longer want the agent to write. (inferred, check the README)
Prompt for your agent
Use the Hycli MCP server (command `hycli`, args `mcp`) to prepare <site-url>, list its actions, and ask me before enabling writes. After I approve, create one draft post on <site-name>. Expected output: a confirmation that the draft was created. Verify the draft appears in the site account before anything is published.
Caveat. Once writes are enabled for a CLI, the agent can run write actions on that site, so turn writes off when you are done.
Get 5 new use cases every morning. Free, one short email, 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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