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

# Connect your IDE

> Browse a connector's schemas and folders, and run bounded SQL, from Cursor or any MCP client

Every connector has its own [MCP](https://docs.timbal.ai/mcp-integration/index.md) endpoint (streamable HTTP). Point an IDE or an agent at it and you can browse that server's databases, run bounded SQL and explore its shares, without writing `curl`.

```text theme={"dark"}
https://api.timbal.ai/orgs/{org_id}/connectors/{connector_id}/mcp
```

The connector is identified by the URL on every request, so a session can never drift to another server. Add one entry per connector.

## Set it up in Cursor

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

```json theme={"dark"}
{
  "mcpServers": {
    "timbal-connector-erp": {
      "url": "https://api.timbal.ai/orgs/<org_id>/connectors/<connector_id>/mcp",
      "headers": { "Authorization": "Bearer <api_key>" }
    }
  }
}
```

To find `<connector_id>`:

```bash theme={"dark"}
curl "https://api.timbal.ai/orgs/$ORG_ID/connectors" -H "Authorization: Bearer $API_KEY"
```

> [!WARNING]
>
> The API key in `mcp.json` is an **organization-wide** key. Protect the file like a credential and never commit it to version control. Keys limited to one connector are planned.

## Tools

| Tool | What it does | Role needed |
| - | - | - |
| `connector_status` | Online or not, version, capabilities | Membership |
| `list_connections` | The connection names configured on the server | Membership |
| `list_tables` | Tables of one connection | Membership |
| `list_columns` | Columns of one table | Membership |
| `describe_table` | Indexes, foreign keys, constraints, size | Membership |
| `list_filesystems` | The share names configured on the server | Membership |
| `fs_ls` | List one folder of a share | Membership |
| `fs_du` | Summarize a folder tree: counts, bytes, largest files, extensions | Membership |
| `query` | Run bounded SQL | ConnectorsManage |
| `fs_search` | Search file contents | ConnectorsManage |

Suggested order for a database: `connector_status`, `list_connections`, `list_tables`, `list_columns` or `describe_table`, then `query`.

Suggested order for files: `connector_status`, `list_filesystems`, `fs_du` on a candidate folder, `fs_ls`, then `fs_search` if you need to look inside.

Try a prompt such as: *"Using the timbal-connector-erp tools, list the tables in `erp` and describe the ones about customers."*

## Behaviour

* The tools do exactly what the equivalent [HTTP requests](https://docs.timbal.ai/connect/sync-data.md) do: same limits, same capability checks, same audit entry for `query` (marked `via=mcp`).
* The connection's [`query` setting](https://docs.timbal.ai/connect/connections#the-query-setting) on the server still decides what `query` may do.
* Every tool except `connector_status` needs the connector online; `connector_status` still answers when it is offline. A connector that is offline, or lacks a capability, returns a tool error with the same message as the API. Nothing here can reach a server the connection can't.
* It does **not** start jobs or syncs, copy files into a knowledge base, or push configuration. For those, use the [API](https://docs.timbal.ai/connect/sync-data.md).

## Next steps

> [card] [Sync your data](https://docs.timbal.ai/connect/sync-data.md)
>
> Start a job or schedule a sync.

> [card] [MCP integration](https://docs.timbal.ai/mcp-integration/index.md)
>
> Connect Timbal's own tools to your IDE.


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