agentleFS
Sign inStart free
SirjanSinghSirjanSingh/oahelper-mcp/skills/oahelper-setup/SKILL.md

oahelper-setup

Skill2 starsChanged 27 days agoMITView on GitHub

Install, connect and troubleshoot the oahelper MCP server (oahelper-mcp) in Claude Code, Claude Desktop, Cursor, VS Code, Codex or any MCP client. Use when the user says "set up oahelper", "oahelper isn't connecting", "session rejected", "daily cap reached", "the oahelper tools are missing", or asks how to refresh their OAHelper cookie.

  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create .env in the data folder if it does not exist.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Set up and fix oahelper-mcp

Part of oahelper-mcp by Sirjan Singh.

The session cookie is a password. Never ask the user to paste it into chat, never print .env, and never echo a header value back. Check whether a key is set, not what it is.

1. Find the install

Work out which way it was installed:

  • Claude Code plugin (oahelper@oahelper-mcp in claude plugin list): the cookie is set with /plugin configure oahelper@oahelper-mcp.
  • uvx (uvx ... oahelper-mcp in the client config): data folder ~/.oahelper unless OAHELPER_HOME is set.
  • Clone (python .../server.py): data folder is the clone itself.

oahelper_status() prints the data folder when the server is reachable.

2. Diagnose in this order, stop at the first failure

CheckHowIf it fails
Runtimeuvx installs: uvx --version. Clones: python --version is 3.10+Install uv, or a newer Python
Dependencies (clones only)<client's python> -c "import mcp"pip install -r requirements.txt into that interpreter. mcp must be below 2.0
Server startsRun the exact command from the client config by hand: it should sit silently waiting on stdin (Ctrl+C to stop)Read the traceback, fix it
Client registeredClaude Code: claude mcp list. Others: open the config file from the READMEAdd it with absolute paths, restart the client
Session presentoahelper_status() says cookie set: yesWalk the user through the cookie steps below
Session validoahelper_status(online=true) says session validCookie expired: redo the cookie steps

oahelper_status(online=true) costs one live request; plain oahelper_status() costs none.

3. Cookie steps (the user does these, not you)

  1. Create .env in the data folder if it does not exist. Plugin users skip this and, after step 3, paste the cookie into /plugin configure oahelper@oahelper-mcp instead.
  2. Log in at https://www.oahelper.in, open DevTools (F12), Network tab, reload.
  3. Click any request whose URL contains /api/proxy/, copy the full cookie request header into OAHELPER_COOKIE= in .env. Copy authorization into OAHELPER_BEARER= if present.
  4. Save. No restart is needed: the server rereads .env on every request.

4. Common errors

  • session rejected / 401 / 403: cookie expired or the user logged out. Redo step 3.
  • Daily cap reached: by design. Offline tools still work. Only raise OAHELPER_DAILY_CAP if the user explicitly asks, and remind them the cap protects their account.
  • Premium content missing: account is not Pro, or the cache holds a logged-out copy. Retry the call with refresh=true.
  • Client shows "failed" or "connection closed": uvx not on the PATH the client sees, or (clones) a relative path or the wrong Python. Use absolute paths.
  • No module named 'mcp.server.fastmcp': mcp 2.x is installed. Install mcp<2.

Finish by reporting each check as pass or fail in one short list.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free