Connect your agent (MCP)

Jsonify is an MCP server. Connect it to the assistant you already use and that assistant can read your datasets, inspect pipelines and runs, start a run, and hand Jason a brief, all through the same account and the same workspaces you see in the browser.

Server URL

https://factory.jsonify.com/mcp

Transport

Streamable HTTP

Sign-in

OAuth, with your Jsonify account

Scope

The organisations you authorise

What you can do from an assistant

• Read data. List datasets, look at a dataset’s columns and versions, and pull rows with a filter. The assistant can then reason about them, chart them, or fold them into whatever it is doing.
• Inspect pipelines and runs. Read the active version, last run status and schedule, plus published output names and row counts.
• Start a run. Run an activated pipeline with a row cap.
• Ask Jason for work. Build a new pipeline, change an existing one, or ask “why did last night’s run fail?” Jason works in a normal Jsonify chat; the assistant relays questions and the outcome.
• Ask questions. “Which retailer raised prices most this week?” becomes a dataset read and an answer, in your assistant.

The connector does not expose arbitrary SQL or file uploads. Ask Jason through request_work to edit pipelines or change their schedules.

Tools

A workspace holds the pipelines, datasets and schedules for one brief. A new brief becomes a workspace after you review it and agree to build.

Preparation and Jason’s test runs are free. Workspace builds and production or scheduled runs count rows against the workspace’s monthly allowance.

Three things to try

• Build: “Track competitor product prices and availability, refreshed daily.”
• Query rows: “Show me 10 rows from my Book prices dataset, including title, price, availability and product URL.”
• Check status and repair: “Check my Book prices pipeline’s latest run status and ask Jason when it was last repaired and what changed.”

The assistant uses get_pipeline for recorded status. Repair questions go through request_work and get_conversation; the pipeline summary does not include a last-repair field.

Need help? Email support@jsonify.com.

Connect your client

Pick your client.

Claude

Claude.ai and the desktop app:

1. Open the directory. Go to Settings → Connectors and select Browse connectors, or open claude.ai/directory/connectors/jsonify directly.
2. Connect. Select Connect next to Jsonify, and sign in to Jsonify when asked.
3. Enable it in a chat. In a new chat, open + → Connectors and enable Jsonify. Then describe the data you need.

On a Team or Enterprise plan, your workspace owner enables Jsonify once for everyone from Admin settings → Connectors. Jsonify is a community connector in the directory — some admins allow those by default, some review them first.

If the directory is not available to you, add it by hand: Settings → Connectors → + Add custom connector, name it Jsonify, paste https://factory.jsonify.com/mcp, then Connect.

Claude Code, in a terminal:

claude mcp add --transport http jsonify https://factory.jsonify.com/mcp
claude mcp login jsonify

The second command opens a browser to sign in. Choose the organisation the assistant should have access to.

ChatGPT

Jsonify is available on the ChatGPT plugin store, so there is nothing to configure.

1. Open the app. Go to Jsonify on the ChatGPT plugin store, or search the store for Jsonify under Data & Analytics.
2. Connect. Select Connect and sign in to Jsonify, or create a free account.
3. Use it in a chat. Type @Jsonify in any chat, or pick it from + → Apps, then describe the dataset you want. Jsonify opens pipelines, datasets and dashboards inside the conversation.

On a Team or Enterprise workspace, an admin may need to approve apps before they appear. If the app directory is not available to you, add the server by hand: enable Developer mode under Settings → Security and login, open Plugins, select +, name it Jsonify, paste https://factory.jsonify.com/mcp and choose OAuth.

Copilot and Teams

Microsoft 365 Copilot reaches Jsonify through an agent built in Copilot Studio.

1. Add the tool. Open your agent in Copilot Studio. Go to Tools → Add a tool → New tool → Model Context Protocol.
2. Point it at Jsonify. Name it Jsonify, paste https://factory.jsonify.com/mcp, and configure OAuth 2.0. Create a connection, sign in, and add the tool to your agent.
3. Publish. Test the agent, then publish it. Open Channels → Teams and Microsoft 365 Copilot, enable Make agent available in Microsoft 365 Copilot, then select Add channel.
4. Install in Teams. Choose See agent in Teams → Add. In Microsoft 365 Copilot, type @, select your agent and ask your question.

Requires Copilot Studio access. Your administrator may need to configure OAuth or approve the agent.

Codex

codex mcp add jsonify --url https://factory.jsonify.com/mcp
codex mcp login jsonify

Cursor

In Cursor’s MCP settings, add a new server named Jsonify of type Streamable HTTP with the URL https://factory.jsonify.com/mcp, then complete the sign-in when Cursor opens the browser. The equivalent configuration entry is:

{
  "mcpServers": {
    "jsonify": { "url": "https://factory.jsonify.com/mcp" }
  }
}

Other assistants

In your assistant’s connections settings, add a remote MCP server named Jsonify. Use Streamable HTTP and OAuth, then sign in to Jsonify. The assistant must support remote MCP servers with OAuth; API-key-only clients cannot connect.

Connect from the Integrations page

Jsonify can walk you through the same steps and confirm the sign-in worked.

1. Open the dialog. Integrations → AI → Connect AI, then ChatGPT, Claude & Microsoft Copilot. The dialog is titled Connect your assistant.
2. Follow the guide. On the Connect tab, “Connect ChatGPT, Claude, or Microsoft Copilot to Jsonify. Follow the setup guide, then return here to check your connection.” Go to jsonify.com/connect ↗ opens the guide for your assistant. For any other assistant, the Advanced tab shows the Server URL to add in its MCP settings, with Copy.
3. Check connection. Back in the dialog, press Check connection. When one connection is found, the dialog reads “{assistant} connected to Jsonify. Return to your assistant to use Jsonify.” and Done closes it.

Back returns to the service list; Close leaves the dialog. “Your assistant appears here and on the conversations it starts. Its access follows your membership in the organization you authorize.”

The organisation requirement

An assistant connection is a grant on your account, made through your Jsonify sign-in, for one or more organisations. Three consequences:

• You need a Jsonify account with an organisation. Sign up in the browser first if you have not; the connection then sees every workspace in the organisations you authorise, subject to your membership at the time of each request. Leave an organisation and the assistant loses it too.
• Brand-new users can start from the assistant. If you sign in during the connection without an organisation yet, the assistant can still describe what you want. Jason prepares a brief, and the assistant gives you a link to review it, accept the terms, create your organisation and start the first build in the browser. Reconnect afterwards so the assistant is authorised for the new organisation.

Starting from an assistant without an account

If you connect before you have a Jsonify organisation, the flow looks like this:

1. Describe what you want in the assistant, as you would to Jason. The assistant starts a preparation and relays Jason’s questions.
2. Open the link the assistant gives you. It shows the brief Jason prepared and the free allowance, asks you to accept the terms, creates your organisation, and starts the first build in the browser.
3. Reconnect the assistant. Sign in through the connection again so it is authorised for the new organisation. The assistant picks up the same workspace and chat rather than starting another build.
4. Review and accept. When the first run has published, look at the dataset. Telling the assistant you are happy marks the workspace live, the same as Open workspace in the browser.

A preparation waits up to 24 hours for you to open the link; after that, start again.

Conversations started from an assistant

Every request an assistant makes through request_work is a real Jason conversation in the workspace. It appears in Conversations with the assistant’s name and icon as the source, so a teammate can see what was asked from where. You can open it in the browser at any time, add to it, or stop it. Closing the assistant does not stop work already handed to Jason. Jason deletes a pipeline or a dataset only when you explicitly ask it to; other changes are made as new versions.

Managing connections

Assistant connections are on the AI tab of the Integrations page, under Assistant connections. Each card shows the assistant’s name, “Use Jsonify from your assistant. Connected to your account across workspaces.”, “Connected” or “Access blocked”, and a menu with Disconnect.

Click a card to open the connection’s page. The header shows its status, “Assistant connection” and “Your account · all your workspaces”. It has two tabs:

• Settings. “This connection is per user. It belongs to your account, not this workspace, so it’s shared across all your workspaces. Teammates connect their own assistants.” Below that, the Connection block with the Server URL and the Client identifier, each with Copy.
• Disconnect. Disconnect {assistant} removes the assistant’s authorisation from your account in every workspace, after a confirmation. Its tokens stop working immediately. Conversations it started stay; stop any active work from its conversation.

• Connections belong to you, not the workspace. They cannot be moved into folders or bulk-deleted with workspace integrations; open the card to disconnect.
• “Access blocked” means Jsonify has cut the connection off but the assistant has not yet released its grant. The Settings tab says so; press Disconnect again to finish.

An assistant connection carries your whole membership. If you share a computer with someone, disconnect before you hand it over.

Troubleshooting

What’s next