Deep Research by OpenHelm

Conduct comprehensive research projects using a virtual computer equipped with a real browser, coding tools, document creation capabilities, and more.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Deep Research Company: Run deep buy-side research on a company: business model, latest financials with dates, recent material SEC filings, the bull/bear case, and the single most important recent chan
  • Earnings Triage: Triage a company's latest earnings: consensus vs actual EPS with the surprise %, key guidance changes, and the highest-leverage questions for management. Use right after a print to ge
  • Track Insider And Congress Trades: Track disclosed corporate-insider (SEC Form 4) and congressional (STOCK Act) trades as alpha signals, and surface clusters where multiple distinct filers bought the

What data it sees

Do you need an account

No: the server works without sign-in

Conduct comprehensive research projects using a virtual computer equipped with a real browser, coding tools, document creation capabilities, and more.

Deep Research by Openhelm enables your agent to tackle work such as:

• Market and competitor analysis • Industry and company research • Investment and acquisition due diligence • Technical and scientific investigations • Report generation with sources and evidence

What makes OpenHelm the best solution for this:

• Research is continuously reviewed and refined by a powerful AI to maximise accuracy and completeness • Uses a highly capable stealth browser that can access more of the web than traditional research agents • Multi-step workflows allow findings to be validated, expanded, and synthesised automatically • Generates structured outputs rather than simply returning search results

For high-stakes research that requires depth, accuracy, and persistence, OpenHelm provides a secure remote environment where complex investigations can be completed autonomously.

How to connect

How to connect Deep Research by OpenHelm to Claude

The server address to paste into Claude settings:

https://deep-research-by-openhelm.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Deep Research by OpenHelm to ChatGPT

The server address to paste into ChatGPT settings:

https://deep-research-by-openhelm.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Deep Research by OpenHelm to Cursor

The server address to paste into Cursor settings:

https://deep-research-by-openhelm.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (9)

Raw names from tools/list. Only developers need these.

deep_research_companyRun deep buy-side research on a company: business model, latest financials with dates, recent material SEC filings, the bull/bear case, and the single most important recent change. Sources are official (SEC EDGAR) and the live web — never fabricated. Use this for investment diligence, a coverage initiation, or a quick but rigorous company workup. Returns a structured summary with cited figures.
earnings_triageTriage a company's latest earnings: consensus vs actual EPS with the surprise %, key guidance changes, and the highest-leverage questions for management. Use right after a print to get the read-through fast. Returns the surprise, guidance deltas, and management questions.
track_insider_and_congress_tradesTrack disclosed corporate-insider (SEC Form 4) and congressional (STOCK Act) trades as alpha signals, and surface clusters where multiple distinct filers bought the same name in the same window. Use to monitor 'who is actually buying' across a watchlist. Returns scored, clustered trade signals (lagged; not advice).
build_comp_setBuild a comparable-companies (comp set) table: peers across growth, margin, and valuation multiples, each with as-of dates and sources, plus a narration of the divergences. Use for relative-value work or a sector comp refresh. Returns the comp table and the cheap/expensive read.
monitor_sec_filingsMonitor recent SEC filings for a set of tickers and flag material disclosures (8-K events, 10-K/10-Q items, Form 4 activity) with a one-line 'why it matters' and a page/section reference. Use as a filings watch. Returns the flagged disclosures with links.
expert_call_briefPrepare a one-page expert-network call brief: background on the speaker and their relevance, your thesis, and the four highest-leverage questions to ask. Use before an expert call. Returns the brief.
screen_sectorRun a thematic sector screen: map incumbents, fast-movers, and newly funded/public entrants, and surface what changed this week plus the names worth a closer look. Use for weekly market maps. Returns the screen.
morning_notesProduce pre-market morning notes for a watchlist: overnight news, price-moving headlines, and new SEC filings per ticker, each with a 'so what' and a sentiment score. Use to start the day briefed. Returns one note per ticker.
check_resultRetrieve the result of a previously started OpenHelm task. Use this when an earlier tool returned status "running" together with a task_id — call check_result with that task_id to get the finished result (or the current status if it's still running). Returns the structured result, confidence, evidence (screenshot URL + matched text), and usage when the task has succeeded.