About TractorScope
TractorScope's MCP server is for teams using SQL dashboards with their own data. AI clients can read databases and dashboards, as well as create or edit charts, filters, and alerts. It connects to the hosted service through OAuth 2.1 with read-only or read-write consent.
Key features
- 01Inspect database schemas and run queries
- 02View and manage dashboards
- 03Create, edit, and retrieve chart data
- 04Manage filters and alerts
- 05Manage share links and embed domains
Use cases
- 01Query business data and create charts
- 02Update dashboard charts and filters
- 03Create alerts for data metrics
MCP support
The hosted Streamable HTTP MCP server connects clients using OAuth 2.1 with PKCE. Its tools cover databases, dashboards, charts, filters, alerts, and sharing settings, with read/write annotations.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.tractorscope.com/mcpclaude mcp add --transport http com-tractorscope https://api.tractorscope.com/mcp{"mcpServers":{"com-tractorscope":{"type":"http","url":"https://api.tractorscope.com/mcp"}}}Open in Cursor{"servers":{"com-tractorscope":{"type":"http","url":"https://api.tractorscope.com/mcp"}}}Open in VS Code{"mcpServers":{"com-tractorscope":{"type":"http","url":"https://api.tractorscope.com/mcp"}}}{"mcpServers":{"com-tractorscope":{"serverUrl":"https://api.tractorscope.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMETractorScope MCP server
TractorScope is a SQL dashboard builder for teams that own their data. This is its hosted Model Context Protocol 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.
Registry
server.json in this repository is the listing published to the official MCP Registry under com.tractorscope/mcp.
Support
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.