Keep your TradingView watchlists in sync with your own stage tags
An agent proposes adds and removals for your own TradingView watchlists when your stage tags change, shows you the diff first, and only writes after you confirm.
How it works
- Read today's stage-change list (see the stage classification use case).
- Load {{stage_to_list_map}} so each stage tag maps to a watchlist you already own.
- Export and save a backup of each watchlist before building the diff.
- Read the current contents of your watchlists through the TradingView MCP tools or an export file.
- Build a diff: which names would move between lists.
- Refuse the run if proposed changes exceed {{max_changes}} or would empty a list.
- Show you the diff and wait for your confirmation.
- Apply only the confirmed changes if your MCP server can update those watchlists; otherwise emit an import CSV for you to upload. Log the confirmed rows.
Copy-paste prompt
You maintain my own TradingView watchlists. You never create alerts, never place orders and never post anything.
1. Read {{stage_changes_csv}} and the current watchlists (TradingView MCP list tools if they can see my lists; otherwise {{watchlist_export_csv}}).
2. Produce a diff table: list name, action (add/remove), reason (the stage change).
3. Stop and ask me to confirm. Do not write anything before I reply "confirm".
4. After confirmation, apply exactly the confirmed rows only if the MCP server can update those watchlists. If it cannot, give me an import CSV per list and stop. Report what changed.
{{stage_changes_csv}} has at least these columns: symbol, old_stage, new_stage.
Use {{stage_to_list_map}} to map each stage tag to a watchlist name, and {{max_changes}} as the cap on rows per run.
Build the diff only from symbols present in {{stage_changes_csv}} or the current list export. Never invent symbols.
Stop without writing if the diff has more than {{max_changes}} rows or would empty a list.Guardrails
- Diff report before every write.
- Writes only to your own watchlists.
- Keep an export of each list before changes so you can restore it.
- Never add or remove a symbol that is not in the stage-change file or the pre-change export.
- Hard cap on changes per run; do not write if the diff would empty a list.
- A backup export must exist before any write or import file is produced.
What can go wrong
Without a diff step, a bad input file can empty a watchlist in one run. Keep a backup export and cap the number of changes per run.
Why it helps
Watchlists drift. Syncing them from written stage rules keeps the list you look at every morning honest.
Set-up notes
- Map each of your stage tags to a TradingView watchlist you already own.
- Prefer TradingView's CSV export/import unless you have checked that your MCP server can list and update those same lists.
- Run in dry-run mode for a week before allowing writes. Keep a backup export of each list and cap how many names can change in one run.
Source and references
Original write-up by Agents for Traders. Background reading is linked below.
- How to import or export a watchlist · TradingView Help Center (checked 17 Oct 2026)
- Model Context Protocol: introduction · modelcontextprotocol.io (checked 17 Oct 2026)
Spotted an error, or want your post removed? Email hello@agentsfortraders.com.
Educational content only. Not investment advice or a personal recommendation. No tickers, signals or trade alerts. Trading involves risk of loss.
Conteúdo exclusivamente educativo. Não constitui aconselhamento nem recomendação de investimento. Sem tickers, sinais ou alertas de negociação. Negociar envolve risco de perda.
Related use cases
Classify your watchlist by trend stage every night
Each evening an agent applies your own numeric rules to label watchlist names by Weinstein stage (1-4) and logs only label changes that persist for your chosen minimum weeks; output goes to your journal after you review a diff.
Watchlists & alert hygieneGive every price alert an expiry date and clear stale ones weekly
An agent applies only the mechanical expiry and duplicate rules you give it to a TradingView alert list you supply (a file you copied, or a local read-only MCP output), and produces a dry-run clean-up table. It never judges which levels matter.
The Daily 3
Three agent workflows for swing traders, free, on US trading days.