Skip to content

Connect company apps to Claude and ChatGPT

To connect company apps to Claude and ChatGPT, connect each account once in Elaichi, share it, and add one URL to both. No MCP server to run.

Raajshekhar Rajan Updated 11 min read
Google Workspace, Slack, Jira and Salesforce accounts connected once to a single organization-wide MCP endpoint, which Claude and ChatGPT both reach for every person in the company

Claude, ChatGPT, Cursor and Microsoft Copilot all sign into the same address, https://api.elaichi.ai/mcp. The same endpoint serves every organization. The OAuth grant behind each token, not the URL, decides which organization and which person a client reaches.

That matters as soon as the requests arrive. An IT lead gets the same request from three teams in one week. Support wants Zendesk in Claude. Sales wants Salesforce in ChatGPT, and engineering wants Jira in both. Answered one at a time, that is four setups, three permission models and three places to check when someone leaves.

This guide shows how to connect company apps to Claude and ChatGPT once, for the whole company. MCP (Model Context Protocol) is the standard way an AI assistant calls tools in other apps. Elaichi serves every connected account through that one endpoint, the web address a client calls. People sign in to it with OAuth, the standard that gives a client a revocable grant instead of a password.

Can you connect every company app to Claude and ChatGPT at once?

Yes for the address, no for the sign-in. One address covers every app the organization connects, and each person connects their client once and approves their own grant.

A grant covers one organization and one person. Every call made with its tokens acts as the person who approved it, and Elaichi re-reads the grant on each request. A rollout is therefore one admin step per client, plus one sign-in per person.

The number of apps does not change that. In Elaichi, connected tools are never listed one by one, however few there are. A model finds a connected tool with search_tools and runs it with execute_tool, and where Code Mode is available, run_code runs them too. Connecting a twenty-first app in Elaichi adds nothing to any client's tool list.

How do you connect company apps to Claude and ChatGPT at once?

Connect each account once in Elaichi, share it, and add one address to each AI client. All of your apps then reach both clients in one pass. Work in this order: accounts first, sharing second, clients last.

  1. Connect each account, such as Slack, Jira and Salesforce, once in Elaichi.
  2. Share each connection, or a toolbox built from it, with the people who need it.
  3. Bring people into the organization with a role already set.
  4. Add https://api.elaichi.ai/mcp once in Claude and once in ChatGPT.
  5. Sign in as one member, run a read in each app, and check the audit trail.

The same address serves Claude, ChatGPT, Cursor, Microsoft Copilot and any MCP client. Adding Cursor later is the same work. Under the default consent choice, a new app needs no change in any client.

Can Google Workspace, Slack, Jira and Salesforce reach Claude for the whole company?

Yes. Each is a connector in Elaichi's catalog. Google Workspace arrives as several: Gmail, Google Drive, Google Calendar and Google Docs. A separate Google Workspace connector covers directory users and groups. Slack, Jira and Salesforce are one connector each.

Decide, per app, whose account each connection is. A connection runs on the credential of the person who connected it. Every call through a shared connection therefore reaches the app as that one account.

That suits a team account, such as a Jira site connected by its admin. It does not suit an inbox, or a CRM where each person's own permissions matter. For Gmail and Salesforce, each person connects their own account, once. Each rep's own Salesforce access shows that pattern in full.

Connecting can start inside either client. The chat shows a one-time link with no token in it, so the link exposes no secret.

What is the end-to-end rollout checklist for these four apps?

Work through it in this order: connect, share, roles and restrictions, clients, verification. Doing the clients last means the first person who signs in already has the right apps and the right limits.

1. Connect each account in Elaichi

Connect Google Drive, Google Calendar, Google Docs, Slack, Jira and Salesforce. Add Gmail and the Google Workspace connector if you need mailboxes or the directory.

Connect Slack and Jira with an account whose access suits everyone who will use them, because every call through a shared connection reaches the app as that one account. Have each person connect their own Gmail and their own Salesforce, so each rep's own CRM permissions apply.

2. Share each connection or a toolbox

Share the Slack and Jira connections at use with a team or the whole organization. A use grantee calls tools through the connection, and every call runs on the owner's sign-in to that app.

Build a toolbox instead when a team needs a fixed argument, such as one Slack channel. Leave Gmail and Salesforce unshared: a per-person connection is already each person's own.

3. Set roles and restrictions before anyone signs in

Invite members with a role preassigned, or verify your email domain so colleagues are offered a seat with a default role. SCIM and single sign-on also work. Each member holds exactly one role.

Write restrictions against roles now. A restriction targets a role or one member, never a team or the whole organization. A role that should only read Salesforce needs an allow rule naming its read tools, plus whole-connector allow rules for every other app that role uses, because one allow rule turns on an allowlist for that layer. A change takes about two minutes, so test after that window.

4. Add the address in Claude

On Claude Team and Enterprise, an Owner or Primary Owner adds a custom connector from Organization settings, then Connectors, by clicking Add, hovering over Custom and choosing Web (Anthropic's custom connector guide, checked October 2026). Give it https://api.elaichi.ai/mcp.

Each member then finds it under Customize, then Connectors, usually marked Custom, and clicks Connect to authenticate (same guide, checked October 2026). On Claude Enterprise, a member whose custom role includes Manage access to Libraries can also add a custom connector (same guide, checked October 2026).

5. Add the address in ChatGPT

On ChatGPT Business, only admins and owners can create and publish plugins for custom MCP servers for the workspace (OpenAI's custom MCP servers guide, checked October 2026). Admins and owners create a custom MCP app from Workspace settings, then Apps, then Create (same guide, checked October 2026).

Creating the app means giving the MCP server's endpoint and metadata, picking an authentication mechanism, clicking Scan Tools, completing the authorization prompt, and then clicking Create (same guide, checked October 2026). Publishing is a separate step, from Workspace settings, then Apps, then Drafts, then Publish, and only admins and owners can do it (same guide, checked October 2026). Once published, the app shows in users' Apps settings labeled custom (same guide, checked October 2026).

Connect at least one account the scanning admin can use before running Scan Tools, because search_tools and execute_tool appear only while at least one connected tool is reachable.

6. Verify in the audit log

Sign in as an ordinary member with the default role. Run one read in each of the four apps, then open the audit log in Elaichi. Each connected-tool entry names the person, the connector, the connection the call reached and the MCP client, with the surface recorded as mcp.

The audit log is eventually consistent, so a new entry can take a moment to appear. If a read you expected to be refused succeeded, check whether the restriction change has had its about two minutes.

Do you have to build or run an MCP server for each app?

No. Elaichi authors, maintains and serves most of its 650+ connectors from its own infrastructure, and the rest are app vendors' own MCP servers, so the company runs no MCP server, hosted or local.

Running your own is real work. Under the MCP specification's local transport, the client launches the server as a subprocess on the person's machine (MCP transports). Multiply that by every app and every laptop, and someone installs, updates and secures each copy. A remote server spares the laptops, but somebody still hosts one per app.

App credentials stay out of the clients and out of Elaichi's organization store. Secrets live in a separate credential service, which encrypts them at rest and refreshes the tokens. If a refresh fails, the connection becomes needs_reauth. That is one account to reconnect, not silent failures in fifty chats.

When the catalog lacks an app, a custom connector is authored from JSON config. Creating one needs the connector:create permission, which Elaichi flags as high trust. Running MCP servers yourself compares the two shapes in depth.

How do connected accounts become tools in a toolbox?

On their own at first, and on purpose when you need limits. Every connection a person holds use on joins their "Everything I can use" set as soon as it exists. There is no build step.

A toolbox is a saved set of tools from one or more connections, shared with a team. It earns its place in two cases. The first is a fixed argument, such as the one Slack channel a team may post to. One condition: a freeze binds only calls made through its toolbox entry, so share the toolbox with the people it governs, not the connection itself. The second is delegation. A team runs tools through the toolbox without being able to open, see or reshare the connection behind it.

What a person may call is still decided by restrictions, rules about which connectors and which individual tools a target may reach. Write them against roles before anyone signs in. A change takes about two minutes to apply, so test after that window. Locking one tool argument walks through a frozen toolbox entry.

How do you share one setup so nobody else has to configure it?

Share the connection or the toolbox, and let people join with a role already set. Sharing in Elaichi is a grant of view, use or edit on a resource. It goes to one person, a team or the whole organization, and use lets the grantee run tools through it.

A member sees only what they own or what was shared with them. No org-level permission widens that view, for owners and admins as well.

People join in four ways. An emailed invite link can carry a role and teams. A verified email domain offers new people a seat with a default role, and they choose to join. SCIM, a standard for syncing users from a directory, provisions them, and single sign-on can add them on first sign-in. Each member holds exactly one role, so choose the default with care.

What remains for each person is small but real. They connect the connector their admin added, and sign in once. They paste no URL, token or client ID. Under "Everything I can use", an account shared with them later reaches their client with no new step.

Where do you add Elaichi's one address in Claude and ChatGPT?

Once, in each client's admin settings, as a custom connector or a custom app. The address is https://api.elaichi.ai/mcp for every organization, with no trailing slash. Nobody enters a client ID or secret. Claude registers itself through OAuth dynamic client registration (RFC 7591).

In Claude Team and Enterprise, an Owner adds it under Organization settings, then Connectors. Members then connect it under Customize, then Connectors (Anthropic's custom connector guide, as of October 2026). Pro and Max users add it themselves. The Claude walkthrough has every click.

In ChatGPT, full MCP with write actions is available on Business, Enterprise and Edu (OpenAI's custom MCP servers guide, as of October 2026). An admin creates one app under Workspace settings, then Apps, runs Scan Tools and publishes it. Members find it in their Apps settings, labeled custom. Setting Elaichi up in ChatGPT covers the plan details.

One ChatGPT app covers twenty apps or two hundred. In Elaichi, connected tools are never listed one by one, however few there are. The client sees search_tools and execute_tool, which reach every connected app. A new app is a new connection in Elaichi, not a new app in ChatGPT.

Connect at least one account the admin can use before running Scan Tools. Those two tools appear only while at least one connected tool is reachable, and the scanning admin's own grant decides that.

Elaichi's sign-in, then a consent screen with an organization picker and up to four checkboxes. Someone not yet signed in to Elaichi signs in first. If the company enforces SSO for its email domain, other sign-in methods are refused.

A person in one organization finds it preselected. The checkboxes are:

  • Use your connected apps
  • See your organization
  • Make changes
  • Delete things

Everything the client requested starts ticked except delete, which never does. With "Use your connected apps" ticked, a "Toolboxes" row opens a sheet that offers "Everything I can use", the default, or "Only the ones I pick", up to 50 toolboxes. "Everything I can use" covers your toolboxes and the automatic ones for every connected app, including apps added later. It is one page with no steps. Allow stays disabled until an organization is picked, its plan is active and at least one box is ticked.

Each grant belongs to one person. In Elaichi, removing or suspending a member revokes every live grant in the same transaction as the membership change, so a leaver's next call from either client fails.

How do you check that every app reached every client?

Sign in as an ordinary member with the default role, and run one read per app. Most people will hold that role, so it is the view that matters.

  1. The client's tool list shows search_tools and execute_tool. If both are missing, no connected tool is reachable. The usual causes are a connection that is absent, pending or needs_reauth, a grant without "Use your connected apps", or a role without tool:execute.
  2. Ask for one read per app, such as today's calendar or an open Jira issue. A search naming an app the person never connected returns nothing, plus a line naming up to six apps they can reach.
  3. Open the audit trail. Elaichi writes one entry for each connected-tool call that reaches execution (a call refused earlier writes none), naming the account each call reached. Each entry records the surface, mcp for a remote client, and the OAuth client the call came through. Claude, ChatGPT and Cursor are named and marked verified.
  4. In Elaichi, Settings, then Connected apps lists the person's client. That is also where they disconnect it.

What goes wrong, and where do you look?

Two failures cover most rollouts: the tools do not appear, or sign-in never finishes. Each has its own checklist.

If the client connects but no tool shows up, the missing-tools checklist walks the causes in order, from a connection that needs re-authentication to a role without tool:execute. In Elaichi, connected tools are never listed one by one, however few there are. An empty-looking list is therefore not proof that nothing is connected.

If sign-in or consent fails, the OAuth error guide names the broken step. A consent link works once and lasts about 30 minutes, so an expired link means starting again from the client.

What do you give up by putting every app behind one address?

Per-tool control inside the AI client. The client sees search_tools, execute_tool and Elaichi's own operations, never a connected app's own tool names, so a client control that picks individual MCP tools acts on those wholes.

Claude sets a connector's tools to Always allow, Needs approval or Blocked, per connector, per category or per tool (Anthropic's connectors article, checked October 2026). Pointed at Elaichi, that setting can only cover execute_tool as a whole, and it does not reach run_code or the toolbox operations. Per-app and per-tool rules move into Elaichi instead, written as restrictions on a role or on one member.

Approval prompts move the same way. Elaichi marks execute_tool destructive and open-world, because the tool it runs is not known before the call. A client that asks before anything not marked read-only therefore asks on every connected-tool call, reads included.

Elaichi is a second vendor and a second bill, and Gold lists at $15 per user per month in USD, or $10 per user per month billed annually (see the pricing page). And one address is one place to get wrong: a restriction written against the wrong role reaches Claude, ChatGPT, Cursor and Microsoft Copilot at once, about two minutes later.

When is a client's own connector enough without Elaichi?

When one person needs one app. A person reading one app through the client's own connector needs nothing more, and a second vendor adds cost without adding control.

The case changes with the second app, the second team or the first contractor. At that point you have several permission models, and no one place to end a person's access. When you don't need an MCP gateway yet lists the signals in detail.

Cost is the other honest limit. Elaichi's Gold plan lists at $15 per user per month in USD, or $10 per user per month billed annually, and the pricing page shows your region's price. Auditor, Guest and Billing Admin seats are not billed. Every new workspace starts on a 14-day Black trial, no credit card to start. Buying Gold or Black during the trial keeps its remaining days rather than granting a fresh 14, so it is one continuous trial, and the seats are first charged when it ends. A workspace that buys nothing moves to the free Personal plan.

Engineers on Cursor use the same address, as the Cursor rollout shows. To plan which team goes first, start from the use-cases directory. If nobody has the time to set it up, forward deployed engineers can do it with you.

FAQ

Frequently asked questions

Can one setup connect 20 or more SaaS apps to ChatGPT Enterprise?

Yes, with Elaichi. A ChatGPT Enterprise admin creates one custom app from Elaichi's address and publishes it to the workspace. Every app the company connects in Elaichi is reached through that one app, because connected tools are found through two tools, search_tools and execute_tool. Adding a twenty-first app is a new connection in Elaichi, not a new app in ChatGPT.

Does Elaichi host the MCP servers, or do we run them?

Neither is on you. Elaichi authors, maintains and serves most of its connectors from its own infrastructure, and the rest are app vendors' own MCP servers that Elaichi governs, so a company runs no MCP server for any app. A separate credential service holds each connected account's secrets, encrypted at rest, and refreshes their tokens. When the catalog lacks an app, a custom connector can be authored from JSON config.

Does each employee have to configure anything for Claude or ChatGPT?

Very little. An admin adds Elaichi's address once in each client, and the apps are shared in Elaichi. Each employee then connects the connector in their own client and signs in with OAuth once. Nobody pastes a URL, an API token or a client ID, and apps shared with them later need no new step.

What happens when we revoke a connection or an app's access?

It stops on the next call. Elaichi re-reads the grant on every MCP request, so disconnecting an app under Settings, then Connected apps, fails that app's very next request. Revoking a share on a connection, or disconnecting the account itself, takes effect on the caller's next call too, and removing or suspending a member revokes their grants the same way. Role and restriction changes are slower, and take about two minutes.

How much does a company-wide Elaichi rollout cost?

Elaichi's Gold plan lists at $15 per user per month in USD, or $10 per user per month billed annually, and elaichi.ai/pricing shows the price in your region. Auditor, Guest and Billing Admin seats are not billed. Every new workspace starts on a 14-day Black trial, no credit card to start. Buying Gold or Black during the trial keeps its remaining days rather than granting a fresh 14, so it is one continuous trial, and the seats are first charged when it ends. A workspace that buys nothing moves to the free Personal plan.

Put AI to work in your own apps

14 days of Black, no credit card. Start with one app and one team.

When the trial ends, nothing is deleted. You move to the free Personal plan, and connections, roles and the audit log stay where they are.

Add one link to your AI app

The same link for everyone on your team.

https://api.elaichi.ai/mcp
  • ChatGPT
  • Claude
  • Cursor
  • Microsoft Copilot