# Zesty.io MCP connector The Zesty.io connector lets Claude, ChatGPT, Cursor, or any MCP client look up your Zesty.io instances, see who has access to each one and what role they hold, with every request tied to the person who signed in. Source: https://elaichi.ai/connectors/zesty/ ## Facts | | | | --- | --- | | Application | Zesty.io | | Category | Application Development | | AI tools | 5 | | 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 Zesty.io is connected - Which Zesty.io instances do I have access to? - List all users and roles on our marketing instance. - Show every instance where Priya holds an admin role. ## Connect Zesty.io in Elaichi This happens once for the organization, before any client is involved. 1. Open Connections, choose Add connection, and pick Zesty.io. 2. Optionally set Share with, then press Connect. 3. Paste a Zesty.io API key. One person generates a token in Zesty.io 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 Zesty.io tools are exposed, rename them, or freeze arguments before anyone points a client at it. ## Connect Zesty.io 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 Zesty.io 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 Zesty.io 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 Zesty.io 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 Zesty.io 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 Zesty.io through Elaichi ### See which Zesty.io instances you own Marketing. Ask for a list of every Zesty.io instance your team runs, with names and IDs, before planning a site refresh or a new campaign microsite. ### Pull up one instance's details fast Web. Give the instance ID and get back its details in seconds, without opening the Zesty.io manager and clicking through the accounts view. ### Check who has access to a site IT. List every user on a Zesty.io instance ahead of a handover or a vendor change, so nobody is surprised by an unfamiliar name. ### Review roles across every Zesty.io instance Security. Ask which users hold owner or admin roles on each instance, then flag anyone whose role is broader than their job needs. ### Map a person to their instances Operations. When someone moves teams or leaves, list every Zesty.io instance they belong to so offboarding covers all of them. ### Audit client instances in one pass Agency. Agencies running several client sites can ask for all instances and their users at once, and turn the answer into a quarterly access report. ## Frequently asked questions ### How do I connect Zesty.io to Claude? Connect Zesty.io in Elaichi by pasting a Zesty.io API key when prompted. There is no OAuth application to register and no client ID or secret to generate. Then in Claude open Customize, then Connectors, then Add, and paste the endpoint https://api.elaichi.ai/mcp. Sign in as yourself and Zesty.io instances appear in Claude. ### Does Zesty.io work with ChatGPT and Cursor as well as Claude? Yes. Once Zesty.io 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 Zesty.io once and every client picks it up. ### What can an AI agent actually do with my Zesty.io data? With this connector an agent can list your Zesty.io instances, pull up one instance by its ID, list the users on an instance, show which role each of those users holds, and list every instance a given user belongs to. It is a read-only view of instances and access, useful for access reviews, handovers, and offboarding checks. ### Does connecting Zesty.io give the AI access to every instance? No. Every request runs as the person who signed in, so the AI sees only the Zesty.io instances and users that person's API key can already reach. Elaichi can narrow that further with restrictions, and it never widens what Zesty.io itself allows. ### Can my team share one Zesty.io connection? Yes. One person connects Zesty.io in Elaichi and shares the connection with a team, and nobody else ever handles the API key. Each teammate still signs in to Elaichi as themselves, so the audit log records who asked for which Zesty.io instance or user list. ### Can I stop an agent from changing or deleting things in Zesty.io? This Zesty.io connector only reads instances, users, and roles, so it cannot change or delete anything. On top of that, Elaichi restrictions work per action, and a blocked action is never shown to the AI client, so no prompt can reach it, for example if you want to hide the list of users with roles from a particular team. ### What happens to a Zesty.io connection when someone leaves? Offboarding a person in Elaichi ends their access to Zesty.io through every client at once. If they connected a shared Zesty.io connection, it keeps working for everyone else on the team. Disconnecting Zesty.io once in Elaichi removes it from Claude, ChatGPT, Cursor, and every other client together. ## All 5 Zesty.io tools Every tool below is callable through https://api.elaichi.ai/mcp once Zesty.io is connected, subject to the toolbox it is in and the restrictions on the caller. - **List all Zesty.io instances** (List). List all instances a user has access to in Zesty. Returns fields such as ZUID (unique identifier), name, domain, createdAt, updatedAt, blueprintZUID, screenshotURL, and other metadata for each instance. - **Get single Zesty.io instance by ID** (Get). Get a specific instance in Zesty.io by id (ZUID). Returns ZUID, name, domain, createdAt, updatedAt, and screenshotURL fields providing key instance details. - **List all Zesty.io instance users** (List). List all users for a specific instance in Zesty.io. Requires instance_zuid. Returns each user's ZUID, email, firstName, lastName, role, and timestamps for creation and updates. - **List all Zesty.io instance users with roles** (List). Get all users of a specific instance in Zesty.io using instance_zuid. Returns each user's details including ZUID, email, name, and their associated Role with its permissions and metadata. - **List all Zesty.io user instances** (List). Get user-instances for a specific user in Zesty.io using user_zuid. Returns instance details including name, ZUID, domain, blueprintZUID, createdAt, and updatedAt fields in the response.