tractorscope-mcp

# TractorScope MCP server

[TractorScope](https://tractorscope.com) is a SQL dashboard builder for teams that own their data. This is its hosted [Model Context Protocol](https://modelcontextprotocol.io) server: connect an AI client and it can read your dashboards, query the databases you have connected, create and edit charts, manage filters and alerts, and pull chart data, all against your own account.

```
https://api.tractorscope.com/mcp
```

Nothing to install. The server speaks streamable HTTP and signs you in with OAuth 2.1 (PKCE, dynamic client registration), so any client that supports remote MCP servers connects with the URL alone.

Full documentation: **https://tractorscope.com/docs/mcp-server**

## Connect

| Client | How |
| --- | --- |
| Claude Desktop / claude.ai | Settings → Connectors → Add custom connector → paste the URL |
| Claude Code | `claude mcp add --transport http tractorscope https://api.tractorscope.com/mcp` |
| Codex | `codex mcp add tractorscope --url "https://api.tractorscope.com/mcp"` then `codex mcp login tractorscope` |
| Cursor | `{"mcpServers":{"tractorscope":{"url":"https://api.tractorscope.com/mcp"}}}` in `~/.cursor/mcp.json` |
| VS Code | `{"servers":{"tractorscope":{"type":"http","url":"https://api.tractorscope.com/mcp"}}}` in `.vscode/mcp.json` |
| Gemini CLI | `{"mcpServers":{"tractorscope":{"httpUrl":"https://api.tractorscope.com/mcp","oauth":{"enabled":true}}}}` in `~/.gemini/settings.json` |
| opencode | `{"mcp":{"tractorscope":{"type":"remote","url":"https://api.tractorscope.com/mcp","enabled":true}}}` in `opencode.json` |

On the consent screen you choose whether the connection may only read, or read and write. Connections are listed and can be revoked under **Settings → MCP Server** in the app.

## Tools

| Area | Read | Write |
| --- | --- | --- |
| Databases | `list_databases`, `get_database_schema`, `query_database` | |
| Dashboards | `list_dashboards`, `get_dashboard`, `list_dashboard_folders`, `search` | `create_dashboard`, `update_dashboard`, `clone_dashboard`, `create_dashboard_folder` |
| Charts | `get_chart`, `get_chart_data`, `pull_chart_data` | `create_chart`, `update_chart`, `clone_chart`, `delete_chart`, `set_chart_fields`, `set_chart_series` |
| Filters | `list_filters` | `create_filter`, `apply_filters_to_dashboard` |
| Alerts | `list_alerts` | `create_alert`, `run_alert_check` |
| Sharing and embedding | `list_share_links`, `list_domains` | `create_domain`, `revoke_domain` |

Every tool is annotated with whether it reads or writes, and whether a write can remove something, so clients can auto-approve reads and confirm the rest. `query_database` runs SELECT only and caps results at 1,000 rows.

## Things to try

- "Which of my dashboards mention revenue? Open the Q3 one and tell me what each chart is showing."
- "Query the orders database for weekly order counts over the last twelve weeks, then put it on my Sales dashboard as a line chart."
- "Make the bars on the Signups by plan chart use our brand colours: Pro in purple, Team in green."
- "Create an alert that emails me when yesterday's failed payments go above twenty."
- "Clone the Executive Overview dashboard into the Board folder and remove the churn chart from the copy."

## Privacy

The server acts as the signed-in user and can only reach what that user can see in the app. Database credentials are never sent over the connection. How TractorScope handles data is described in the [privacy policy](https://tractorscope.com/privacy-policy).

## Registry

`server.json` in this repository is the listing published to the [official MCP Registry](https://registry.modelcontextprotocol.io) under `com.tractorscope/mcp`.

## Support

help@tractorscope.com