# Dixa MCP connector The Dixa connector lets Claude, ChatGPT, Cursor, and the Elaichi Agent read the custom attributes set up in your Dixa account, so anyone can ask what fields exist and how each one is defined. Source: https://elaichi.ai/connectors/dixa/ ## Facts | | | | --- | --- | | Application | Dixa | | Category | Ticketing | | AI tools | 2 | | Authentication | Connects with an API key | | Needs your own OAuth app | No | | MCP endpoint | https://api.elaichi.ai/mcp | | Works with | Claude, ChatGPT, Cursor, any MCP client, and the Elaichi Agent | | Tools advertised by name | Yes | ## What you can ask once Dixa is connected - List all Dixa custom attributes used on conversations. - Show the Dixa custom attribute behind ticket priority. - Which Dixa custom attributes are missing values this week? ## Connect Dixa in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Dixa. 2. Optionally set Share with, then press Connect. 3. Paste a Dixa API key. One person generates a token in Dixa and pastes it once. Everyone else works through Share with, and never sees it. Credentials are vaulted and nobody, including the AI, reads them back. The connection becomes a toolbox immediately, so you can curate which Dixa tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Connect Dixa to Claude Endpoint: https://api.elaichi.ai/mcp 1. Open Customize, then Connectors. 2. Press Add. 3. Name it, paste the MCP server URL, then Continue. 4. Sign in and approve. On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves. ## Connect Dixa to ChatGPT Endpoint: https://api.elaichi.ai/mcp 1. Open Plugins, then press the + button. 2. Name it and paste the endpoint into Server URL. 3. Leave Authentication on OAuth, then tick the risk acknowledgement. 4. Press Create, then sign in and approve. Works on the web today. The plugin directory lives at chatgpt.com/plugins. ## Connect Dixa to Cursor Endpoint: https://api.elaichi.ai/mcp 1. Open `~/.cursor/mcp.json`. 2. Add the endpoint under `mcpServers`. 3. Reload Cursor, then sign in and approve. Set up per machine, so repeat it on each computer you work from. ## Connect Dixa to any MCP client Endpoint: https://api.elaichi.ai/mcp 1. Add the endpoint as a remote MCP server. 2. Sign in and approve. The Elaichi Agent already has these tools, with nothing to set up. ## What the consent screen decides Only Read is granted by default, which is not enough to call a Dixa tool. Over MCP there is no trusted place to confirm a write in the moment, so the consent screen is the standing approval rather than a formality. Grant Read and Run tools. Think hard before granting Delete, which reaches into connected apps and cannot be undone. ## What teams do with Dixa through Elaichi ### Check which conversation fields agents must fill Support. Ask which custom attributes are set up in Dixa before a shift starts, so nobody guesses at field names or picks the wrong one when tagging a conversation. ### Look up the options behind a dropdown Support operations. Pull a single Dixa custom attribute by its ID and see exactly which values it offers, useful when someone asks why a reason code is missing from the list. ### Spot duplicate or stale attributes Quality assurance. List every custom attribute in Dixa and ask the AI to point out fields with near-identical names or labels that no longer match how the team works. ### Write the handbook page on Dixa fields Enablement. Draft a plain-language guide to every custom attribute in Dixa, with its label, type, and options, without copying anything by hand from the admin screen. ### Confirm the field a report depends on Analytics. Before building a dashboard on a Dixa attribute, check its ID, type, and current options so the report matches what agents are actually able to select. ### Review attribute setup after a Dixa change IT. After an admin edits fields in Dixa, ask for the full list of custom attributes and compare it with last week's to confirm only the intended changes landed. ## Frequently asked questions ### How do I connect Dixa to Claude? Connect Dixa in Elaichi first: paste a Dixa API key from your Dixa settings, since Dixa connects with an API key and there is no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp as the endpoint. Sign in to Elaichi when prompted and Dixa is available in Claude. ### Does Dixa work with ChatGPT and Cursor as well as Claude? Yes. Once Dixa is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client, and the Elaichi Agent. You connect Dixa once and every client sees it. ### What can an AI agent actually do with my Dixa data? With this connector an agent can read the custom attributes defined in Dixa: the list of every field, plus the details of any one field such as its label, type, and the options it offers. That means you can ask which fields agents fill on a conversation, what values a dropdown allows, or whether two attributes overlap. It does not create, edit, or delete anything in Dixa. ### Does connecting Dixa give the AI access to my whole Dixa account? No. Access to Dixa follows the API key that was used to connect, and the AI can only read what that key can read, which through this connector is limited to custom attributes. Elaichi can narrow that further with restrictions, and it never widens what the Dixa key itself allows. ### Can my team share one Dixa connection? Yes. One person connects Dixa with the API key and shares the connection with a team in Elaichi, and nobody else ever sees or handles that key. Each teammate still signs in to Elaichi as themselves, so every question asked of Dixa is logged under the name of the person who asked it. ### Can I stop an agent from deleting or changing things in Dixa? This Dixa connector is read-only, so an agent cannot delete or change custom attributes through it. Restrictions in Elaichi also work per action, and a blocked action is never shown to Claude, ChatGPT, Cursor, or any other client, so no prompt can reach it. ### What happens to a Dixa connection when someone leaves? When a person is offboarded in Elaichi their access to the Dixa connection ends immediately, in every client they had set up. A shared Dixa connection keeps working for everyone else on the team. If you want to remove Dixa entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client at the same time. ## All 2 Dixa tools Every tool below is callable through https://api.elaichi.ai/mcp once Dixa is connected, subject to the toolbox it is in and the restrictions on the caller. - **List all Dixa custom attributes** (List). List all custom attributes in Dixa. Returns id, entityType, identifier, label, inputDefinition, description, createdAt, updatedAt, isRequired, isArchived, and isDeactivated fields for each custom attribute. - **Get single Dixa custom attribute by ID** (Get). Get custom attribute by id in Dixa. Returns id, entityType, identifier, label, inputDefinition, description, createdAt, updatedAt, isRequired, isArchived, and isDeactivated.