# Tray.ai MCP connector

The Tray.ai connector lets Claude, ChatGPT, Cursor, Microsoft Copilot and any MCP client list, create and upgrade solution instances, manage users and authentications, and export or import projects, with every call running under the person who signed in.

Source: https://elaichi.ai/connectors/trayai/

## Facts

| | |
| --- | --- |
| Application | Tray.ai |
| Category | IPAAS |
| AI tools | 19 |
| Authentication | Connects with an API key |
| Bring your own OAuth app | No |
| MCP endpoint | https://api.elaichi.ai/mcp |
| Works with | Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client, and the Elaichi Agent |
| Tools advertised by name | No. Connected tools are never listed one by one, however few there are. The endpoint advertises `search_tools` and `execute_tool` instead |

## What you can ask once Tray.ai is connected

- Which solution instances are still on an old version?
- List every Tray.ai authentication created this month
- Export the config for the onboarding project

## Connect Tray.ai in Elaichi

This happens once for the organization, before any client is involved.

1. Open Connections, choose Add connection, and pick Tray.ai.
2. Optionally set Share with, then press Connect.
3. Paste a Tray.ai API key. One person generates a token in Tray.ai 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 Tray.ai tools are exposed, rename them, or freeze arguments before anyone points a client at it.

## Tray.ai MCP connector for 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.

## Tray.ai MCP connector for Claude Code

Endpoint: https://api.elaichi.ai/mcp

1. In a terminal, run `claude mcp add` with the endpoint.
2. Start Claude Code and run `/mcp`.
3. Pick elaichi, then sign in and approve in the browser.

```bash
claude mcp add --transport http elaichi --scope user https://api.elaichi.ai/mcp
```

Use `--scope project` instead to share it with the repository through `.mcp.json`.

## Tray.ai MCP connector for 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. The plugin directory lives at chatgpt.com/plugins.

## Tray.ai MCP connector for 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.

## Tray.ai MCP connector for Microsoft Copilot

Endpoint: https://api.elaichi.ai/mcp

1. In Copilot Studio, open your agent, then Tools, Add a tool, New tool and Model Context Protocol.
2. Paste the endpoint into Server URL, choose OAuth 2.0, then Dynamic discovery, and press Create.
3. Create a new connection, sign in and approve, then press Add to agent.
4. Under Channels, open Teams and Microsoft Copilot and make the agent available in Microsoft Copilot.

Microsoft Copilot was called Microsoft 365 Copilot. Keep the tool on end-user credentials, so each person signs in as themselves.

## Connect Tray.ai 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

Every scope the client asks for starts ticked except "Delete things", which you tick yourself. Calling a Tray.ai tool needs "Use your connected apps". 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. Think hard before granting Use your connected apps, which can also delete in connected apps and cannot be undone.

## What teams do with Tray.ai through Elaichi

### Set up a solution instance for a new customer

Customer success. Ask for a new instance of the onboarding solution for the account that just signed, and have the agent create it and confirm it is live.

### Upgrade every instance to the latest version

Customer success. Find which solution instances are still on an old version and upgrade them one by one, or all at once, from a single request.

### Review every connected account in one place

IT. List all Tray.ai authentications, spot the ones nobody recognizes, and delete the stale ones before they become a problem.

### Add a user or clean up after a leaver

IT. Create a Tray.ai user for a new hire, update their details, or delete the account of someone who has left, without opening the admin screen.

### Move a project between environments

Platform. Export a project and its config from sandbox and import it into production, with the agent telling you what was carried across.

### Find out which solutions are running where

Operations. Ask which solutions exist and how many instances each has, then follow up on the ones that look unused or duplicated.

## Elaichi vs Zapier MCP vs Composio for Tray.ai

All three can connect Tray.ai to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.

| What to check | Elaichi | Zapier MCP | Composio |
| --- | --- | --- | --- |
| Where the AI connects | One address for the whole organization. Endpoint: https://api.elaichi.ai/mcp | A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Tray.ai tools | Allow or restrict single Tray.ai tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Tray.ai call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | Free for one person; $15 per user per month on Gold. | 2 tasks per successful call. | Billed per tool call. |

Sources: Zapier MCP [docs](https://docs.zapier.com/mcp/get-started/quickstart), [security](https://docs.zapier.com/mcp/manage/security), [usage](https://docs.zapier.com/mcp/features/usage); Composio [docs](https://docs.composio.dev/docs/composio-connect), [gateway](https://composio.dev/mcp-gateway), [enterprise](https://composio.dev/enterprise), [pricing](https://composio.dev/pricing). Checked September 2026.

Longer take: [Zapier MCP alternative](/blog/zapier-mcp-alternative/) and [when you don't need an MCP gateway](/blog/when-you-dont-need-an-mcp-gateway/).

## Frequently asked questions

### How do I connect Tray.ai to Claude?

Connect Tray.ai in Elaichi by pasting a Tray.ai API key. There is no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude signs you in to Elaichi and Tray.ai is available in your chat from then on.

### Does Tray.ai work with ChatGPT and Cursor as well as Claude?

Yes. Once Tray.ai is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, Microsoft Copilot, any MCP client and the Elaichi Agent. You connect Tray.ai once and every client picks it up.

### What can an AI agent actually do with my Tray.ai data?

An agent can list your Tray.ai solutions and solution instances, create or upgrade an instance, add, update or delete users, review and delete authentications, and export or import projects and their config. Short, concrete asks work best, such as which instances are still on an old version. The agent searches for the right action and runs it for you.

### Does connecting Tray.ai give the AI access to everything in my account?

No. An agent can only reach what the Tray.ai API key you connected can reach, and each person signs in to Elaichi as themselves, so every call is tied to them. Elaichi can narrow that access further with restrictions, and it never widens it beyond what Tray.ai already allows.

### Can my team share one Tray.ai connection?

Yes. One person connects Tray.ai 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 names the person who created an instance or deleted a user, not the person who connected the account.

### Can I stop an agent from deleting or changing things in Tray.ai?

Yes. Restrictions in Elaichi work per action, so you can allow listing Tray.ai solutions and instances while restricting deleting users or authentications, on a role or on one person. A restricted action still appears in Elaichi's tool search, flagged as restricted, but no client can run it, whatever the prompt says.

### What happens to a Tray.ai connection when someone leaves?

Offboarding a person in Elaichi ends their access to Tray.ai through every client at once. A Tray.ai connection they were sharing keeps working for everyone else on the team. If you want Tray.ai gone entirely, disconnecting it once in Elaichi removes it from Claude, ChatGPT, Cursor, Microsoft Copilot and every other client together.

### Does the Tray.ai MCP connector work with Gemini, Codex, Claude Code or other MCP clients?

Yes. Tray.ai is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, Microsoft Copilot, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.

### Is Elaichi an alternative to Zapier MCP for Tray.ai?

Yes. Both let Claude, ChatGPT or Cursor use Tray.ai. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Tray.ai call.

### How is Elaichi different from Composio for Tray.ai?

Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Tray.ai: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.

## All 19 Tray.ai tools

Every tool below is callable through https://api.elaichi.ai/mcp once Tray.ai is connected, subject to the toolbox it is in and the restrictions on the caller.

- **List all Tray.ai authentications** (List). List Tray Embedded authentications available to the viewer, with connector details. Returns edges whose node includes id, name, customFields, and service (id, name, icon, title, version). Paginated by cursor.
- **Create a Tray.ai authentication** (Create). Create a Tray Embedded user authentication for a service connector. Returns: id. Required: name, service_id, service_environment_id, authentication_data. hidden defaults to true.
- **Delete a Tray.ai authentication by ID** (Delete). Delete a Tray Embedded authentication by id. Returns: data. Required: id. Any workflow currently using the authentication will break, so recreate it in the target organization or workspace instead of moving it when possible.
- **List all Tray.ai solutions** (List). List the Tray Embedded solutions available to your End Users. Returns data.viewer.solutions with edges of solution nodes (id, title, description, tags, customFields, configSlots, authSlots) and pageInfo cursors. Supports cursor-based pagination; no required parameters.
- **List all Tray.ai users** (List). List Tray embedded end users in your org. Returns: id, name, externalUserId, isTestUser, authType, authId. Cursor-paginated.
- **Update a Tray.ai user by ID** (Update). Update a Tray embedded end user by id, e.g. rename the user or toggle their test-user status. Returns: id, name, externalUserId, isTestUser, authType, authId. Required: id.
- **Tray.ai users create user token** (Create). Create a user access token for a Tray embedded end user. Returns: accessToken, authType, authId. Required: user_id.
- **Delete a Tray.ai user by ID** (Delete). Delete a Tray embedded end user by id. The user can no longer edit or access their instances or trigger new ones, though running executions are completed. Returns: clientMutationId, authType, authId. Required: id.
- **Tray.ai users generate authorization code** (Generate). Generate a one-time-use authorization code for a Tray embedded end user, for use in the Auth dialog or Config Wizard url. Returns: authorizationCode, authType, authId. Required: user_id.
- **Get single Tray.ai user by ID** (Get). Get a Tray Embedded end user by id. Returns: id, name, authType, authId. Required: id.
- **Create a Tray.ai user** (Create). Create a Tray Embedded end user. Returns: userId, authType, authId. Required: name, external_user_id.
- **List all Tray.ai solution instances** (List). List solution instances in Tray.io. Returns the solutionInstances connection under data.viewer.solutionInstances: each edge node carries id, name, enabled, owner, created, solutionVersionFlags, workflows, authValues, and configValues, with pageInfo cursors.
- **Create a Tray.ai solution instance** (Create). Create a solution instance for an end user from a Tray.io solution. Returns the created instance's id, name, enabled, created, and workflows under data.createSolutionInstance.solutionInstance. Required: solution_id, name.
- **Update a Tray.ai solution instance by ID** (Update). Update a Tray.io solution instance by id — rename it and/or enable or disable it. Returns the updated instance's id, name, enabled, and created under data.updateSolutionInstance.solutionInstance. Required: id, name, enabled.
- **Delete a Tray.ai solution instance by ID** (Delete). Delete a Tray.io solution instance by id; its underlying workflows stop after completing their currently executing steps. Returns the removeSolutionInstance confirmation payload with clientMutationId. Required: id.
- **Tray.ai solution instances upgrade** (Action). Upgrade a Tray solution instance to a newer version of its solution, applying new config and auth slot values. Returns the upgraded instance: id, enabled, created, config_values, auth_values. Required: solution_instance_id.
- **Tray.ai projects export** (Export). Export a Tray project as a JSON payload for backup or promotion to another workspace or environment. Returns: exportedProjectJson. Required: project_id.
- **Tray.ai projects import** (Import). Import an exported Tray project into a target project from its exported project JSON. Returns: clientMutationId. Required: exported_project_json, target_project_id.
- **Tray.ai projects export config** (Export). Export the configuration of a Tray project as a JSON payload. Returns: exportProjectConfigJson. Required: project_id.
