Finviz for AI agents
Finviz is a market screening and research tool, giving ELITE subscribers programmatic access to stock screens and filings used by active traders and investors. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Finviz.
Screen stocks by criteria
Run a stock screen against a set of filters to find candidates matching an investment thesis.
Check insider transactions
List insider transactions for a ticker to see recent buying or selling activity.
Read-only portfolio checks
Get a portfolio's holdings as a read-only step before a periodic performance review.
11 Finviz actions, graded by risk.
Every Finviz action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
10Look things up. Allowed by default.
- finviz.list_newsList News
- finviz.list_groupsList Market Groups
- finviz.get_portfolioGet Portfolio
- finviz.list_calendarList Calendar
- finviz.list_investorsList Investors
- finviz.get_options_chainGet Options Chain
- finviz.get_stock_historyGet Stock History
- finviz.list_latest_filingsList Latest Filings
- finviz.list_investor_holdingsList Investor Holdings
- finviz.list_insider_transactionsList Insider Transactions
write
1Create and change things. Allow, or ask the user first.
- finviz.screen_stocksScreen Stocks
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Finviz in three steps.
- 01Your users connect FinvizThey add their Finviz api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “screen Stocks” can wait for the user to approve.
- 03Any agent can actYour agent calls Finviz through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('finviz', { read: 'allow', write: 'ask', // screen_stocks destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Finviz connects.
Users add their Finviz api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Finviz connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Finviz from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Finviz and Arc0, answered.
Can I use Finviz with Claude, ChatGPT or Cursor?
Yes. Connect Finviz to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Finviz actions you allow.
How do users connect Finviz?
Users add their Finviz api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Finviz actions can my agent take?
11 in total: 10 read, 1 write and 0 destructive, such as “screen Stocks”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Finviz?
Yes. Allow read actions and deny writes in the Finviz policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Finviz too?
Yes. The same Finviz connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Finviz into your agent.
Your users connect Finviz once, under your brand. Your agent gets 11 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan