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 · General-purpose

Give your assistant a cloud browser agent it can actually run.

A raw, unopinionated 1:1 mapping of the OpenHelm public API. Write custom instructions, spawn an ephemeral agent run in a browser sandbox, and read back evidence-backed structured JSON, all from ChatGPT, Claude or Cursor.

Connect the server See the tools ↓

General-Purpose

Tool call

Sandbox

Result

Call run_task from my assistant.

now

Assistant called run_task

OpenHelm spun up a cloud sandbox

Working through the task…

Evidence-backed result returned

Where shall we steer?

General-Purpose · live

What it does

The general-purpose server exposes the OpenHelm /v1 engine directly to any MCP client. Instead of a fixed set of opinionated workflows, it gives your assistant the primitives: define a task in natural language, optionally pin a JSON output schema, run it in an isolated cloud browser sandbox, and retrieve structured, evidence-backed results.

It is the right server when you are building custom automations, prototyping in Cursor, or want full control over prompts and output shape rather than a domain-specific toolset.

Endpoint

Add this URL to your MCP client.

Remote MCP URL

https://mcp.openhelm.ai/main/mcp

Local bridge (optional)

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

Tools

What your assistant can call.

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

run_task

Execute an inline natural-language prompt, with an optional structured JSON output schema.

create_project

Establish a container to organise jobs and runs.

list_projects

Fetch the projects belonging to your organisation.

create_job

Store a reusable, named agent task template.

run_job

Trigger an instance of a stored template with input parameters.

list_runs

Retrieve historical run logs.

check_result

Query status and retrieve the results of an active or completed task.

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/main/mcp. No install, no terminal, no Node setup. For clients that need a local bridge, run npx mcp-remote https://mcp.openhelm.ai/main/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.

Prefer to call the engine directly from your own product? The same primitives are available over REST.

Build on the OpenHelm API→

Common questions about the General-Purpose server

Other servers

Explore the rest of the OpenHelm MCP suite.

Investment analysts, VCs & corporate strategy teams

Deep Research

Buy-side research tools, SEC filings, earnings triage, comps, grounded in official sources.

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 →