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

# Sailer MCP

> Two hosted servers. One for the people in your CRM, one for the agents that talk to them.

Sailer MCP lets Claude, ChatGPT, Cursor, and anything else that speaks MCP call
tools against a live workspace. You add a URL, sign in, and ask in plain
language. The model does the rest.

Two servers, not one: dumping both on a model makes it pick worse tools. Connect
the one you actually need.

| Server                  | URL                                     | Live today                            |
| ----------------------- | --------------------------------------- | ------------------------------------- |
| **Sailer CRM**          | `https://mcp.chatsailer.com/mcp/crm`    | Identity, schema, contacts, campaigns |
| **Sailer Agent Studio** | `https://mcp.chatsailer.com/mcp/studio` | Identity, agent graphs, sandbox       |

Start with CRM. Studio is for people who edit agents.

The URL must include `/mcp/` before `/crm` or `/studio`. `/crm` by itself is a
typo, and the client will tell you it cannot reach the server.

## What is live

CRM record tools take a `resource` argument so they can grow. Today the only
value is `"contact"`. Campaigns are live. Organizations, deals, and messages
are not tools yet — OAuth may list those scopes; the tools are not behind them.

Studio inspects an agent's working copy, publishes it, and tests it in a
sandbox. Nothing reaches live conversations until you publish on purpose.

## How it talks

Stateless JSON over Streamable HTTP. There is no SSE stream, no WebSocket, and
no local `stdio` package. Long work — a sandbox turn — is start-then-poll,
because a connection that sits idle dies on the load balancer.

You do not need to know that to connect. Your client does.

## Prove it

Once a client is connected, ask:

> Which Sailer workspace am I connected to?

The model should call `whoami` and name the workspace, the parent organization,
who authorized the connection, and the scopes you granted. That single answer
confirms auth, tenancy, and tool-calling all work.

## Start here

<CardGroup cols={2}>
  <Card title="Connect a client" icon="plug" href="/mcp/connect">
    Claude Code, Claude, ChatGPT, or Cursor. About ten minutes.
  </Card>

  <Card title="Authentication" icon="key" href="/mcp/auth">
    OAuth vs a workspace token, scopes, and why the first connection cannot write.
  </Card>

  <Card title="CRM server" icon="address-book" href="/mcp/crm">
    Contacts, schema, campaigns. Call `describe_schema` before you guess field keys.
  </Card>

  <Card title="Agent Studio" icon="diagram-project" href="/mcp/studio">
    Graphs, publish, sandbox. Draft until you ship.
  </Card>
</CardGroup>