An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect ParseHub to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run headless browser jobs and pull data through your AI client.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through ParseHub.

  1. 01

    List projects

    This capability lists all your ParseHub web scraping projects. It returns project tokens, titles, and configuration details needed for further operations.

  2. 02

    Cancel run

    Use this to stop a queued or active ParseHub run. Any data already scraped during the process is preserved and can be retrieved later.

  3. 03

    Delete run

    This capability permanently removes a ParseHub run and its associated data to help you manage your account storage.

  4. 04

    Get last ready data

    This capability fetches the most recent completed data for a specific project. It is the fastest way to get fresh results without tracking individual run tokens.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through ParseHub.

  1. 05

    Get project

    This capability retrieves the full configuration details for a specific ParseHub project using its project token.

  2. 06

    Get run data

    This capability downloads the raw JSON data from a completed ParseHub run. It only works once the run status is marked as complete.

  3. 07

    Get run details

    Use this to check the current status of a specific ParseHub run. It helps your agent know when to wait for a job to finish.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through ParseHub.

  1. 08

    Run project with URL

    This capability starts a new scraping run using a custom starting URL. It applies your existing project templates to a new target page.

  2. 09

    List runs

    This capability provides a history of all runs associated with a ParseHub project. It is useful for auditing past extractions.

  3. 10

    Run project

    This capability triggers a new scraping run for a pre-configured project. It returns a run token so you can track the job's progress.

Real work

What teams actually run

01

Competitor Price Tracking

Set up a project once and tell your agent to run it daily to fetch new pricing JSON.

02

Automated Lead Generation

Trigger scrapers on directory sites and have your agent parse the contact information immediately.

03

Research Data Collection

Use custom URLs to run scraping templates against specific academic or news sites.

04

Data Pipeline Auditing

Use the agent to list run histories and verify that scraping jobs completed successfully.

Automate a task

Put ParseHub to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

ParseHub works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put ParseHub to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

944ms average. Fast in production.

ParseHub is checked daily against the live service.

Daily averagePeak 1124ms
Oct 3Today
Fastest day
827ms
Slowest day
1124ms
14-day trend
Slowing+15%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of ParseHub, so you can see the experience inside your AI.

It does not authenticate your account with ParseHub. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

ParseHub Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_KQ4Vz5JSUvjaARvQvBDyCn0dVVNm7RhifigMEXcR/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — ParseHub capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "parsehub-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_KQ4Vz5JSUvjaARvQvBDyCn0dVVNm7RhifigMEXcR/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up ParseHub in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work ParseHub owners hand off.

This MCP is built for professionals who need to bridge the gap between web data and automated analysis.

  • 01

    Data Engineers

    They trigger cloud scraping jobs and pipe the resulting JSON straight into data pipelines.

  • 02

    Marketing Intelligence

    They use the agent to monitor competitor pricing and fetch updated product data automatically.

  • 03

    Research Analysts

    They kick off academic or market research scrapers and digest the results through chat.

FAQ

Questions ParseHub owners ask.

  • 01

    How do I use my existing ParseHub templates?

    You can use the run_project or run_project_with_url capabilities to trigger jobs using the configurations you already built in the ParseHub desktop client.

  • 02

    Can I scrape a different website using an old project?

    Yes. Use the run_project_with_url capability to apply your existing extraction rules to a new starting URL.

  • 03

    What happens to data if I cancel a running job?

    If the run was already scraping pages, the data from those pages is preserved and can be retrieved using get_run_data.

  • 04

    Do I need to keep the ParseHub desktop app open?

    No. This MCP handles the communication with the ParseHub cloud, so you can manage everything through your AI client.

  • 05

    How do I get the scraped data into a usable format?

    Your agent can use get_run_data to pull the raw JSON payload, which follows the structure you defined in your ParseHub template.

  • 06

    Do I need the ParseHub Desktop capability running to use this?

    No. This integration operates completely natively via ParseHub's Cloud API endpoints. You only need the desktop app to build the templates originally. All executions mapped here happen on their cloud scaling servers.

  • 07

    Can I provide a different Start URL when running a project?

    Yes. The run_project_with_url command allows you to explicitly provide a start_url query property. This instructs the ParseHub crawler to ignore its project-saved URL and begin parsing the newly mapped domain using the same semantic template.

  • 08

    Is the downloaded data returned in JSON or raw HTML?

    The payload fetched by get_run_data is exported entirely as structured, pre-parsed JSON mirroring the exact template node selections defined in your project architecture.

Explore

More in Developer Tools

Suggestions

Connect ParseHub to Claude, Cursor, ChatGPT & more