> ## Documentation Index
> Fetch the complete documentation index at: https://docs.trevosdk.com/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP

> Review proposals and run experiments from Claude, ChatGPT, Cursor or any MCP client.

TrevoSDK MCP is a hosted [MCP](https://modelcontextprotocol.io) server at
`https://mcp.trevosdk.com/mcp`. It lets an AI app do what the [CLI](/install/cli) does: list what
Trevo proposed, approve or dismiss, ask for a fresh batch, follow generation, and start, end and
decide experiments. Nothing runs on your machine.

## Connect

Add the server to your app. On first use it opens a Trevo sign-in, then a page where you choose:

* **The workspace** it opens. One per connection; connect again for another.
* **What it may change.** Every write is off until you turn it on, and you can only turn on what
  your role allows. Reading the workspace is always included.

### Claude Code

```bash theme={null}
claude mcp add --transport http trevosdk https://mcp.trevosdk.com/mcp
```

Then run `/mcp` in Claude Code and choose **Authenticate**.

### Cursor

Add it to `~/.cursor/mcp.json`, or `.cursor/mcp.json` in a project:

```json theme={null}
{
  "mcpServers": {
    "trevosdk": { "url": "https://mcp.trevosdk.com/mcp" }
  }
}
```

### claude.ai

**Settings → Connectors → Add custom connector**, with the URL above.

### ChatGPT

Add a custom connector with the URL above and **OAuth** as the authentication. Custom connectors
need developer mode, which depends on your ChatGPT plan.

### With an API key

For a script, a CI job or a headless agent, send a workspace API key instead of signing in. Make
one under **Settings → API access**:

```bash theme={null}
claude mcp add --transport http trevosdk https://mcp.trevosdk.com/mcp \
  --header "Authorization: Bearer $TREVO_API_KEY"
```

A key opens its own workspace with its own scopes, as it does for the CLI. Apps that only support
OAuth, such as ChatGPT, cannot use one.

## Tools

| Tool | What it does |
| - | - |
| `proposals_list`, `proposals_show` | Proposals waiting for review |
| `experiments_list`, `experiments_show`, `experiments_status` | Experiments and where each one is |
| `runs_list`, `runs_show` | Proposal generation runs |
| `funnels_list` | The funnels the workspace measures |
| `generate` | Ask for a new batch of proposals |
| `proposals_approve`, `proposals_dismiss`, `proposals_revise` | Review a proposal |
| `experiments_start`, `experiments_pause`, `experiments_resume`, `experiments_end` | Control a running experiment |
| `experiments_decide` | Ship a winner or reject |

Every write is marked as one that changes things, and the server asks the app to confirm with you
first. `generate` and `proposals_approve` answer before the work is done: follow them with
`runs_show` or `experiments_status`, which wait up to 45 seconds per call.

## What it can do

The app acts as you, with the writes you allowed and your role still holds. A write it may not make
gets Trevo's refusal, with the reason. The workspace's audit log records when an app is connected
or disconnected, and each change under your name, marked with the app that made it, for example
"via ChatGPT".

What the app reads from Trevo goes to it and to its model provider, and is handled under that
app's terms. Connect only apps your company allows for this data.

## Disconnect

* **Account → Connected apps** lists the apps you connected, in every workspace.
* **Settings → API access → Connected apps** lists the apps connected to that workspace. Anyone who
  can manage API keys sees and disconnects everyone's.

A disconnected app stops at once. Leaving an organization stops every app you connected to its
workspaces; if you rejoin, they work again until you disconnect them.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.