Do I need to install anything?

No. OpenHelm MCP servers are remote, Streamable-HTTP servers. You add a URL as a remote connector in ChatGPT, Claude, Cursor or another MCP client. Clients without native remote support can use the lightweight npx mcp-remote bridge.

Where does the work actually run?

Not on the MCP endpoint. When a tool is called, OpenHelm starts an asynchronous agent run in an isolated E2B cloud sandbox that drives a real browser and reads official sources. The MCP layer is stateless: it holds no database and stores no secrets.

What happens with long-running tasks?

The server uses a bounded-wait pattern of about 75 seconds. Fast tasks return their structured result in one turn. Slower tasks return a task_id and your assistant calls check_result a moment later to retrieve the finished output, so connections never time out mid-run.

Connecting requires an OpenHelm account with a card on file, which starts a 14-day free trial. You are not charged during the trial. After that, usage runs on your OpenHelm plan.

MCP server · Deep research

A buy-side research analyst inside your AI assistant.

Specialised, domain-grounded tools for investment research. Deep company dives, earnings triage, filings and congressional-trade monitoring, comp sets and morning notes, built on SEC EDGAR and live financial data, with citations and no fabrication.

Connect the server See the tools ↓

Deep Research

Tool call

Sandbox

Result

Call deep_research_company from my assistant.

now

Assistant called deep_research_company

OpenHelm spun up a cloud sandbox

Working through the task…

Evidence-backed result returned

Where shall we steer?

Deep Research · live

What it does

The Deep Research server adapts OpenHelm’s investment-analyst workflows into specialised tools. Rather than generic browsing, each tool runs structured prompts grounded in official sources, SEC EDGAR, company IR pages, live market data, so outputs are quantitative, source-cited investment memos rather than guesses.

It is built for hedge funds, asset managers, VCs and corporate strategy teams who want the structured groundwork, monitoring, triage, comps, briefs, automated, while keeping the investment judgment with their team.

Endpoint

Add this URL to your MCP client.

Remote MCP URL

https://mcp.openhelm.ai/research/mcp

Local bridge (optional)

npx mcp-remote https://mcp.openhelm.ai/research/mcp

Tools

What your assistant can call.

Available on https://mcp.openhelm.ai/research/mcp

deep_research_company

An exhaustive investigation of a business: model, risks and moat analysis.

earnings_triage

Isolate guidance changes, key executive quotes and consensus discrepancies from a fresh print.

track_insider_and_congress_trades

Query and synthesise recent SEC Form 4 filings and congressional STOCK Act disclosures.

build_comp_set

Generate comparable peer tables with valuation multiples and growth-divergence narratives.

monitor_sec_filings

Track material risk-factor changes or accounting divergences across corporate filings.

expert_call_brief

Prepare a target-company brief and high-conviction screening questions ahead of expert calls.

screen_sector

Run thematic macro screens (e.g. software margins, logistics backlogs) across an industry.

morning_notes

Scan overnight filings and market indicators into a pre-market brief.

check_result

Continue polling or retrieve finalised financial artifacts.

Get started

Connect in under a minute.

1
Add the remote server
In ChatGPT, Claude, Cursor or any MCP client, add a remote connector pointing at https://mcp.openhelm.ai/research/mcp. No install, no terminal, no Node setup. For clients that need a local bridge, run npx mcp-remote https://mcp.openhelm.ai/research/mcp.
2
Connect your OpenHelm account
Click Connect and you are sent to app.openhelm.ai/connect to authorise via OAuth 2.1. Your encrypted OpenHelm API key is wrapped in a signed token, the server itself stores no secrets.
3
Add a card to start the trial
New accounts add a card to activate a 14-day free trial (you are not billed during the trial). This keeps the shared cloud compute protected from multi-account abuse.
4
Run tasks from your assistant
Ask your assistant in plain English. It calls the right tool, OpenHelm spins up an isolated cloud browser sandbox, and returns evidence-backed structured results, polling check_result for longer runs.

Want it run for you as a managed service, not just as tools in your assistant? See the full research-analyst offering.

See the hedge fund use case→

Common questions about the Deep Research server

Other servers

Explore the rest of the OpenHelm MCP suite.

Developers, engineering teams & power users

General-Purpose

A raw, unopinionated AI browser agent and run executor, straight from your assistant.

Growth marketers, content directors & SEO specialists

SEO & GEO

Programmatic SEO plus GEO, rank on Google and audit how AI engines cite your brand.

Want it run for you instead?

The MCP servers put the tools in your assistant. If you'd rather we run the whole workflow as a managed service, book a 20-minute call and we'll scope it.

Book a demo Build on the API →