Skip to main content
Everything you need is one URL, and it is the same for every assistant:
There is nothing to switch on inside Exec. Your normal Exec login authorizes the connection, and your existing Exec permissions are what it gets. Sign-in is handled by Exec, so there is no API key to generate, paste, or rotate, and no client ID or secret to fill in. If a tool offers advanced OAuth fields, leave them blank.

​
Find your tool

Each section below is self-contained, so you only need to read your own.

Claude

Desktop and web

Claude Code

Terminal

ChatGPT

Desktop and web

Codex

Terminal

Microsoft Copilot

Microsoft 365 and Teams

GitHub Copilot

VS Code, Visual Studio, JetBrains

Cursor

Editor

Anything else

Any MCP client

​
Claude

The desktop app and claude.ai. Available on Free, Pro, Max, Team, and Enterprise, though Free allows only one custom connector in total.
1

Owner: add Exec to the organization

Only on Team and Enterprise, and only an Owner can do this. Go to Organization settings > Connectors, click Add, hover Custom and choose Web, then paste the URL and name it Exec.
On an individual plan, skip this step.
2

Add or find Exec in your own connectors

Go to Customize > Connectors. On Team or Enterprise, Exec is already listed and shows as not connected. On an individual plan, click +, choose Add custom connector, paste the URL above, and click Add.
3

Sign in to Exec

Click Connect. A browser tab opens on an Exec page titled Connect to Exec. Enter your work email, then sign in with single sign-on or your Exec password.
4

Choose a workspace, if asked

Only if you belong to more than one Exec workspace. The connection is bound to whichever you pick.
5

Turn it on in your chat

In a conversation, click + at the lower left, open Connectors, and make sure Exec is on.
6

Check it worked

Ask:
Your own recent sessions should come back.
Claude has no way to edit a connector once it exists. If the URL or the name needs changing, remove it and add it again.

​
Claude Code

One command in your terminal:
1

Add the server

This adds it for the current project. Add --scope user to make it available in all your projects, or --scope project to share it with your team through a checked-in .mcp.json.
2

Sign in to Exec

Run /mcp inside Claude Code, choose Exec, and follow the browser prompts. Your token is stored and refreshed automatically.You can also run claude mcp login exec directly.
3

Check it worked

​
ChatGPT

Available on Plus, Pro, Business, Enterprise, and Education, but not on Free. Custom MCP servers live under Plugins, and they require Developer mode.
1

Turn on Developer mode

In ChatGPT, open Settings > Security and login and switch on Developer mode. Nothing below appears until you do.ChatGPT shows a broad caution here about connectors that can change or delete things. That caution applies to Exec: it can make changes such as assigning a roleplay or enrolling someone in a course, always with your own Exec permissions and always previewed before it runs. It cannot delete anything.On Business and Enterprise workspaces, Developer mode can be restricted by workspace policy, so you may need your ChatGPT admin here.
2

Create the connection

Go to chatgpt.com/plugins and click +. Give it a name and description, such as Exec and “Practice and performance data from our Exec workspace.”
3

Point it at Exec

Under Connection, paste the URL, including the /mcp on the end:
Create the connection, then review the tools it discovered. Your new app appears under Drafts.
4

Sign in to Exec

The same Exec sign-in page as everywhere else. Enter your work email, then sign in with single sign-on or your Exec password.
5

Enable it for a conversation

ChatGPT does not use it automatically. In a chat, open the Plus menu, choose Developer mode, and select Exec for that conversation.
6

Check it worked

Name Exec in your first message, or ChatGPT may answer from general knowledge instead of reaching for the connector.

​
Codex

The Codex CLI, the ChatGPT desktop app, and the Codex IDE extension share one configuration, so you set this up once.
1

Add the server

The --url flag is what makes this a remote server rather than a local command.
2

Sign in to Exec

Sign-in does not happen automatically here. Run:
A browser opens on the Exec sign-in page. Add --no-browser if you would rather paste the URL yourself.
3

Check it worked

Run codex mcp list to confirm Exec is there, then ask:
Inside the Codex TUI, /mcp shows which servers are active.
Editing the config file instead. The command above writes to ~/.codex/config.toml. You can add the same thing by hand:
Then run codex mcp login exec as above.
The ChatGPT desktop app and the IDE extension read this same file, but you need to restart them to pick up a change. Both also offer a settings screen: MCP servers > Add server, choose Streamable HTTP, paste the URL, then use the Authenticate action on the row.ChatGPT on the web is different. It does not read your local Codex configuration at all. There, use the ChatGPT steps above instead.

​
Microsoft Copilot

Microsoft 365 Copilot connects to Exec through an agent in Copilot Studio. Somebody builds the agent once and shares it, and each person signs in to Exec the first time they use it.
1

Add Exec to an agent

In Copilot Studio, open an agent and go to Tools > Add a tool > New tool > Model Context Protocol. Name it Exec and paste the URL:
2

Choose Dynamic discovery

For authentication, choose OAuth 2.0 > Dynamic discovery and select Create. There is no client ID or secret to enter.
3

Sign in to Exec

Select Create a new connection, sign in on the Exec page that opens, then select Add to agent. Make sure the connection uses End user credentials, so each person sees Exec with their own permissions rather than yours.
4

Publish and check it worked

Publish the agent to the Teams and Microsoft 365 Copilot channel and share it. Then ask:
If Copilot asks you to connect first, select Open Connection Manager, connect Exec, then Retry.

​
GitHub Copilot

Copilot Chat in VS Code, Visual Studio, and JetBrains IDEs uses MCP tools in Agent mode.
1

Add Exec to your MCP config

Create or edit .vscode/mcp.json in a project, or run MCP: Add Server from the Command Palette and choose Global to make Exec available in every project:
The top-level key is servers, where most other tools use mcpServers. Visual Studio and JetBrains IDEs read the same format.
2

Sign in to Exec

The first time Exec starts, VS Code asks whether you trust the server. Trust it, and a browser opens on the Exec sign-in page. In Visual Studio, select Auth in the line of links above the server entry in mcp.json.
3

Check it worked

Switch Copilot Chat to Agent mode and ask:
On Copilot Business and Enterprise, MCP servers are off until an organization owner turns them on under Organization settings > Copilot > Policies > Features > MCP servers in Copilot. If Exec never starts, ask them to enable it.

​
Cursor

1

Add Exec to your MCP config

Create or edit ~/.cursor/mcp.json to make Exec available everywhere, or .cursor/mcp.json in a project to keep it to that project:
A remote server needs only url. The type field is for local servers.
2

Sign in to Exec

Open the Customize page in the sidebar, find Exec in the MCP list, and use the sign-in prompt on its row. A browser tab opens on the Exec sign-in page.
3

Check it worked

If nothing happens, open the Output panel and select MCP Logs.
On Cursor Enterprise, admins can restrict which MCP servers run, under Team Settings > MCP Configuration. If Exec never appears, ask them to allowlist https://api.exec.com/mcp.

​
Any other MCP client

Exec speaks the standard Model Context Protocol, so anything supporting remote MCP servers over HTTP can connect. Paste the URL wherever your tool asks for a custom MCP server, then sign in.
If your tool takes a JSON config file rather than a URL field, this is the same connection:
Your tool needs two things:

​
Using a local config file

Two reasons to take this route: your client can only run an MCP server as a local process, or you are on a Team or Enterprise plan and would rather not wait for an owner to add the connector. A small bridge makes the remote server look local:
This needs Node.js 18 or newer, and the Exec sign-in appears the first time the connection is used. If sign-in gets stuck, deleting the ~/.mcp-auth folder and restarting your client clears it.
This also sidesteps the connector list entirely, which makes it a way to evaluate Exec before your IT team has approved anything. That does mean it sits outside whatever governance your company has around AI tool connectors, so move to the approved route once somebody can approve it.

​
In-house assistants and agents

A connection is always scoped to one person and one workspace. There is no service account, and access is exactly the signed-in person’s Exec permissions, so an agent acting for a team sees only what the person who authorized it can see. If you already hold an Exec API key it can be used as a bearer token instead of signing in, which suits an unattended service. Treat it carefully: it reads with workspace admin access and does not expire. It cannot make changes, so assigning, enrolling, and inviting need the normal sign-in. For anything a person drives, prefer the normal sign-in. To build directly against Exec rather than through an assistant, see the API Reference.

​
Your assistant will ask before it uses Exec

The first time it reaches for Exec, most assistants ask your permission, usually offering something like ask every time, always allow, or block. This is your assistant’s own setting rather than Exec’s. Always allow is the usual choice for reading your own data. If your assistant later says it cannot see your Exec data even though the connector shows as connected, check whether the capability got blocked here.

​
Staying connected, and disconnecting

Staying connected. It refreshes quietly. In normal use you should not have to sign in again for about a month. Reconnecting is often silent. If you already hold a live authorization and reconnect, you may go straight through with no sign-in and no consent screen, reusing the workspace you picked originally. That is expected. To change workspace, disconnect first. Disconnecting. Remove the connector in your assistant. That ends the whole authorization, not just the current session.
There is no MCP screen in Exec, so disconnecting happens on your assistant’s side. For offboarding you do not need to touch anyone’s assistant: deactivating someone in Exec, or removing them from the workspace, cuts their access on their next request.

​
Common problems

An empty answer usually means the sign-in did not finish. The connection still looks present, so your assistant reports an empty workspace rather than a problem. If an answer you expect comes back empty, reconnect before concluding there is no data.
On Free, Pro, or Max, add it yourself as a custom connector using the URL above. On a Team or Enterprise plan, an owner has to add Exec for the organization before it appears for anyone else. In ChatGPT, check that Developer mode is on. In Microsoft 365 Copilot, Exec appears once someone publishes the Exec agent from Copilot Studio and shares it with you.
The sign-in almost certainly did not complete. Disconnect, reconnect, and make sure you reach the Exec sign-in page and authorize. An unfinished sign-in fails quietly rather than showing an error. If you have several tools connected, it can also mean your assistant used a different one, so try starting with “Using the Exec MCP, …”.
Name it explicitly: “Using the Exec MCP, …”. Common with ChatGPT. Also check the connector is switched on for that conversation.
It is the same sign-in as the Exec app, including the lockout after repeated failed attempts, so somebody locked out of Exec is locked out of connecting until that clears. Reset your password in Exec if needed. If single sign-on sends you back with an error, your email may not be attached to that workspace.
Disconnect the connector and connect again, choosing the right one. The connection is bound to whichever you picked.
Two sign-ins raced each other and one won. Harmless. Reconnect.
Either the capability is blocked in your assistant’s own permission settings, or you genuinely do not have access to that data in Exec. Skill and scenario analytics, for example, are limited to admins and group admins. See What the AI can see.
Charts need an assistant that can display interactive panels. In a text-only assistant you get the numbers instead, which is not a failure. See Limits.
Full troubleshooting guide.

​
Next

Prompts and reliable answers

Prompts by role, ready to copy

Managing your team

The video walkthrough, if you run a team