Getting started

Connect ChatGPT, Claude, Claude Code & Codex

Click-by-click setup for the AI apps people use most — paste the URL and sign in, or use a token — what a working connection looks like, and what to do when one won’t connect.

5 min read

One server, every app. Each connects to the same MCP server described in Connect your AI client to your orgs — this page is the click-by-click version for the ones people actually use, including what “it worked” looks like in each.

Pick the one that matches how you work

ChatGPT, Claude and Claude Code need only the server URL: you paste it in, sign in to orgadmin.ai, and click Allow — no token to copy. Codex and the Claude Desktop extension use a personal access token you create in Settings.

Before you start

  • MCP has to be switched on for this deployment. If the MCP access card in Settings shows a warning, an operator needs to enable it first.
  • A plan that includes MCP access, and at least one connected Salesforce org — see Connect your Salesforce orgs. No app can connect an org for you; that needs a browser sign-in.
  • The app signed in to its own AI subscription. Your subscription pays for the thinking; orgadmin.ai only supplies the Salesforce tools, so no AI key is needed here.
  • The server URL — it's at the top of the MCP access card with a copy button, and it is https://orgadmin.ai/api/mcp.

Claude (web, desktop & mobile)

Claude adds remote MCP servers as custom connectors. Add it once and it works on claude.ai, in the Claude desktop app and on mobile.

  1. Copy the server URL
    https://orgadmin.ai/api/mcp
  2. Add it as a custom connector — In Claude, open Settings → Connectors and choose "Add custom connector". Name it orgadmin.ai, paste the URL, and click Add — nothing else needs filling in. On a Team or Enterprise plan an owner adds it once, under Admin settings → Connectors, and everyone else just connects.
  3. Connect and sign in — Click Connect. Claude opens orgadmin.ai: sign in if you are asked to, choose what Claude may do, and click Allow. You land back in Claude with the connector shown as connected.
  4. Switch it on in a chat — In a conversation, open the tools menu (the + or "Search and tools" button) and turn orgadmin.ai on.

On a Team or Enterprise plan

An owner adds the connector once in Claude's Admin settings → Connectors. Everyone else then finds it under Settings → Connectors and clicks Connect — each person signs in to their own orgadmin.ai account and gets their own access, never a shared one.

ChatGPT

ChatGPT connects to custom MCP servers in developer mode. Menu names move around between ChatGPT versions, so if a label below doesn't match exactly, look for the nearest equivalent.

  1. Copy the server URL
    https://orgadmin.ai/api/mcp
  2. Switch on developer mode — In ChatGPT, open Settings → Apps & Connectors (just Apps in newer versions) → Advanced settings, and turn on Developer mode. On a workspace plan an admin may need to allow it first.
  3. Create the connector — Back in Apps & Connectors, click Create. Name it orgadmin.ai, paste the URL as the MCP server URL, choose OAuth for authentication, confirm you trust the app, and click Create.
  4. Sign in and allow — ChatGPT opens orgadmin.ai: sign in if you are asked to, choose what ChatGPT may do, and click Allow. To use it, pick orgadmin.ai from the + menu in a chat (under Developer mode).

Developer mode is per account

ChatGPT shows a warning when developer mode is on, because a custom connector can read and change data. That is expected. On Business and Enterprise workspaces, an admin may need to allow developer mode or custom connectors before the option appears.

Claude Code

One command adds the server to every project on your machine, then you sign in once. Works the same in the CLI, the desktop app, and the VS Code and JetBrains extensions.

  1. Add the server — --scope user makes it available in every project. Drop it to add the server to the current project only.
    claude mcp add --transport http --scope user orgadmin https://orgadmin.ai/api/mcp
  2. Sign in — Start Claude Code, run /mcp, pick orgadmin and choose Authenticate. Your browser opens orgadmin.ai: sign in, choose what Claude Code may do, and click Allow. Claude Code stays signed in from then on.
  3. Check it connected — Should report "Connected". Inside a session, /mcp shows the same thing plus the tool list.
    claude mcp list
  4. No browser on that machine? Use a token instead — On a server, in CI or over SSH, add it with a personal access token from Settings → MCP access in place of the first command.
    claude mcp add --transport http --scope user orgadmin https://orgadmin.ai/api/mcp --header "Authorization: Bearer oamcp_your-token-here"
  5. Sharing a repo instead? Use .mcp.json — Claude Code expands ${ORGADMIN_MCP_TOKEN} at load time, so this file is safe to commit — each teammate sets their own token in their environment and holds their own scopes.

    In .mcp.json:

    {
      "mcpServers": {
        "orgadmin": {
          "type": "http",
          "url": "https://orgadmin.ai/api/mcp",
          "headers": {
            "Authorization": "Bearer ${ORGADMIN_MCP_TOKEN}"
          }
        }
      }
    }

Two things worth knowing:

  • Tools appear with an mcp__orgadmin__ prefix — that's Claude Code namespacing them, not a different tool set. Ask in plain English; you never type the names.
  • The ready-made prompts show up under / — explore_org, investigate_error, security_review and build_metadata. They carry the ordering knowledge (check automation before proposing a trigger, confirm field names before writing SOQL) that otherwise only the in-app assistant has.

Clients that use a token

Codex and the Claude Desktop extension authenticate with a personal access token rather than a browser sign-in. Create one in Settings → MCP access → Personal access tokens:

  1. 1

    Name it after the machine that will use it

    Codex on my laptop, work desktop. This is what you look for when you revoke one later.
  2. 2

    Tick only the scopes you need

    org:read alone covers reading schema, code, flows, debug logs and SELECT-only SOQL, which is most work. A tool outside your scopes is never even shown to the AI. The full breakdown is in the MCP guide.
  3. 3

    Copy the token before you leave the page

    It is shown once and stored only as a hash — nobody can show it to you again. Lose it and you revoke it and make another.

The setup blocks below are pre-filled in the app

The MCP access card shows the same commands with your new token already in them, and a copy button on each. This page carries oamcp_your-token-here as a placeholder instead, because it's a public page.

Codex CLI

Codex reads its MCP servers from ~/.codex/config.toml and takes the token from an environment variable, so the credential never lands in the config file itself.

  1. Put the token in your environment — macOS and Linux — add it to ~/.zshrc or ~/.bashrc so it survives a new terminal. On Windows, use setx ORGADMIN_MCP_TOKEN "…" and open a new terminal.
    export ORGADMIN_MCP_TOKEN="oamcp_your-token-here"
  2. Add the server — Append this to your Codex config. Codex reads the token from the environment variable at connect time.

    In ~/.codex/config.toml:

    [mcp_servers.orgadmin]
    url = "https://orgadmin.ai/api/mcp"
    bearer_token_env_var = "ORGADMIN_MCP_TOKEN"
    # The first connection wakes the deployment and re-checks your token,
    # which can take longer than the 10s Codex allows by default.
    startup_timeout_sec = 30
  3. Check it connected — Lists the server and its tools. /mcp inside a session shows the same, and names the failure if it did not connect.
    codex mcp list

Two things worth knowing:

  • The variable has to be set where Codex starts. Codex reads it from its own environment at connect time, so putting it in ~/.zshrc (or setx on Windows) and opening a new terminal is the reliable way — exporting it in a shell Codex is already running in does nothing.
  • Codex uses tools and the server's instructions. The prompts and resources this server also publishes are surfaced by clients that support them, such as Claude Code; in Codex you just ask for what you want.

Claude Desktop extension

The Claude connector above works in the desktop app too, and is the simplest route. If you specifically want a token-based install — say, on a machine where you'd rather not sign in through a browser — Settings builds you an extension: a .mcpb file containing a small local bridge and your token. Download it, double-click it, done.

  1. Download the extension — In Settings → MCP access, create a token and click "Download Claude Desktop extension". Your token is packaged inside it, so there is nothing to configure after installing.
  2. Install it — Double-click the .mcpb file, or drag it onto the Claude Desktop window. You can also use Settings → Extensions → Advanced settings → Install Extension…. Claude Desktop may warn that it did not come from its directory, which is expected for a bundle you built yourself. Replacing an existing install: remove the old extension first, since the new file differs only by the token inside it.
  3. Other stdio-only clients: run the bridge directly — Use --probe first to confirm it reaches the server; it performs the handshake, prints what the server offers, and exits. In PowerShell, set the variable with $env:ORGADMIN_MCP_TOKEN = "…" instead of export.
    export ORGADMIN_MCP_TOKEN="oamcp_your-token-here"
    node scripts/mcp-stdio.mjs --url https://orgadmin.ai/api/mcp --probe
  4. …then point the client at it — Use the absolute path to the bridge — these clients do not run in your shell and will not resolve a relative one.

    In the client’s MCP config:

    {
      "mcpServers": {
        "orgadmin": {
          "command": "node",
          "args": [
            "/absolute/path/to/scripts/mcp-stdio.mjs",
            "--url",
            "https://orgadmin.ai/api/mcp"
          ],
          "env": {
            "ORGADMIN_MCP_TOKEN": "oamcp_your-token-here"
          }
        }
      }
    }

The file is a live credential

Anyone who opens that .mcpb has your token and your scopes until you revoke it. Treat it like a password: don't email it, don't commit it, and revoke the token in Settings if it goes astray. Revoking takes effect on the extension's very next call.

Confirm it worked

Whichever app you used, ask it to “use the whoami tool”. It comes back with the orgadmin.ai account the connection is authenticated as, the connection's name, and the exact scopes it was granted:

{
  "account": { "email": "[email protected]", "name": "Your Name" },
  "token": { "name": "Claude" },
  "scopes": ["org:read"]
}

That single call proves the server is reachable, the connection is valid, and which permissions it carries — which is also the fastest way to explain a surprising “tool not found” later. Then try a real one:

  • “List my connected Salesforce orgs.”
  • “What fields are on Opportunity in my sandbox?” — you can name an org the way you named it here; there is no need to paste an id.
  • “What automation runs on Account, and is any of it likely to conflict?”

See and disconnect your apps

Every app you connect by signing in appears in Settings → MCP access as a connected app, next to any tokens you've created, with when it was last used and which orgs it may use. Orgs changes that — for example, making production read only or switching an org off — and applies from the app's next call. Disconnect cuts the app off immediately, mid-conversation if need be; to use it again, reconnect from the app and sign in. Removing the connector inside Claude or ChatGPT stops that app using it — disconnect it here as well if you want to be certain it can't come back. What each connection did is in your MCP activity log.

When it won't connect

Claude and ChatGPT

  • “This link has expired” on the orgadmin.ai page — the sign-in took longer than fifteen minutes, or the page was opened twice. Go back to the app and click Connect again.
  • “Your plan doesn't include connecting AI apps” — MCP access is a paid feature. Choose a plan that includes it, then connect again.
  • ChatGPT has no Create button or MCP option — developer mode is off, or your workspace admin hasn't allowed it.
  • The app says it couldn't reach the server — check the URL ends in /api/mcp and starts with https://. A 404 means MCP is switched off for this deployment.
  • It connected, but a tool you expected is missing — its scope wasn't ticked on the consent screen. Disconnect and reconnect the connector, and tick it this time.

Claude Code

  • “Needs authentication” in /mcp — you haven't signed in yet, or the connection was disconnected. Pick orgadmin there and choose Authenticate.
  • “Failed” on a server added with a token — Claude Code reports a rejected Authorization header as a failed connection rather than offering to sign in. The token is wrong, revoked or expired; add the server again with a fresh one, or without the header to sign in instead.
  • The server is missing in another project — it was added without --scope user, so it belongs to the directory you ran the command in. Add it again with that flag.
  • It tries to run the URL as a program — --transport http was left out, so the CLI read the URL as a command to execute.

Claude Desktop extension

  • The download button is greyed out — the extension can only be built while a freshly created token is on screen, since that is the only moment the token exists in readable form. Create one and it lights up.
  • It installs, then every tool fails — the token inside it was revoked or expired. A bundle can't be re-keyed: create a new token, download a fresh extension, and remove the old extension first. Two downloads differ only by the token inside them, so installing over the top can leave the old one running.
  • A warning that it isn't from the extension directory — expected for a bundle built by your own deployment rather than published to Anthropic's directory.

Codex CLI

  • It gives up while starting the server — the first connection wakes the deployment and re-checks your token, which can take longer than the ten seconds Codex allows by default. Raise startup_timeout_sec in the server's block.
  • It connects but lists no tools — the variable named by bearer_token_env_var isn't set in the environment Codex was launched from. Set it, then restart Codex rather than just starting a new session.

Any client

  • A tool this page mentions is “not found” — the connection doesn't hold its scope, so it was never offered. Scopes are fixed when you click Allow or create a token; reconnect or make a new token. whoami shows what you have.
  • 404 on the endpoint — MCP is switched off for this deployment.
  • Everything worked, then stopped — a disconnected app, a revoked token, a deactivated account, or a Salesforce sign-in revoked upstream all cut access off on the very next call, mid conversation.

Server-side messages — rate limits, sandbox-only writes, results too large — are covered in the MCP guide's troubleshooting section.

Follow along in your own org

This guide sets up MCP Server. 14-day free trial, no credit card.

Start free trial