For the complete documentation index, see llms.txt. This page is also available as Markdown.

MCP Server

Connect AI assistants to a Sling Platform project over MCP Streamable HTTP using a project token

The Sling Platform exposes an MCP server over Streamable HTTP. AI assistants can list files, edit YAML, trigger jobs, and inspect executions with the same project token as the REST API and the sling platform CLI.

This is distinct from the CLI MCP server (sling serve mcp), which talks to local connections over stdio. Use the stdio server for local env.yaml work; use this server for the hosted project. Tool names are disjoint by design.

Setup

  1. Enable the server per project in Settings → Project → Enable MCP Server. The dialog shows the exact URL for your deployment.

  2. Create a project token in Settings → API Tokens.

  3. Point your MCP client at the endpoint with the token header:

URL:     https://api.slingdata.io/mcp     (self-hosted: https://<your-host>/mcp)
Header:  Authorization: Sling-Project-Token <token>

connections.test/discover/preview/exec, compile.replication/spec/monitor, and execs.cancel need an online agent. discover, preview, and exec also need Enable Data Preview. connections.exec accepts a single read-only SQL statement only — use a read-only database user for the complete boundary.

Claude Code
claude mcp add --transport http sling-platform https://api.slingdata.io/mcp \
  --header "Authorization: Sling-Project-Token <token>"
Cursor

Add to ~/.cursor/mcp.json (or .cursor/mcp.json in your project):

{
  "mcpServers": {
    "sling-platform": {
      "url": "https://api.slingdata.io/mcp",
      "headers": { "Authorization": "Sling-Project-Token <token>" }
    }
  }
}
VS Code (Copilot)

Add to .vscode/mcp.json:

{
  "servers": {
    "sling-platform": {
      "type": "http",
      "url": "https://api.slingdata.io/mcp",
      "headers": { "Authorization": "Sling-Project-Token <token>" }
    }
  }
}
Claude Desktop and other stdio-only clients

Bridge with mcp-remote. For Claude Desktop, add to claude_desktop_config.json:

Generic Streamable HTTP

Point any MCP Streamable HTTP client at https://<host>/mcp (POST|GET|DELETE) with the Authorization: Sling-Project-Token <token> header.

Tools

Each tool takes an action and an input object, e.g. {"action": "list", "input": {}}. Call the docs action on any tool first — it returns the full platform guide for that domain.

Tool
Actions
Description

project

docs, get, status, dashboard, settings_test, events, git_status, git_branches, git_diff, git_config_get, platform_status

Project metadata and status, dashboard charts, audit events, git reads (no writes), deployment status.

files

docs, list, get, save, rename, delete

Project YAML/SQL files (replications, pipelines, monitors, specs). save validates by inferred type.

jobs

docs, list, status, get, save, set, trigger, activate, deactivate

Scheduled jobs. save is a full replace — round-trip get first. activate/deactivate patch only the active flag. trigger returns {exec_id} (accepts full_refresh: true); poll execs.status — the server does not push progress. Free plan cannot trigger.

execs

docs, list, status, log, tasks, steps, cancel, delete

Run history and logs. log returns formatted, ANSI-stripped log text (task/status filters; large output is tail-capped). tasks/steps return structured records — each record's output field is the full log text (exclude_output: true to omit). list/status filter by exec_id.

connections

docs, list, test, discover, preview, exec, exec_cancel

Project connections. exec runs one read-only SQL statement (default 100 rows, max 1000; server waits up to 30m). Cancel by client disconnect, or pass query_id and call exec_cancel from another session.

compile

docs, replication, pipeline, spec, monitor

Validate YAML configs. replication/spec/monitor compile on an online agent; pipeline validates server-side. Compile only — execution goes through jobs.trigger.

monitor

docs, history_list, history_trends, trend_details, columns_list, columns_latest, events_list, schema_state_list, runs_list

Read-only monitor history, column stats, schema state, and runs.

agents

docs, list, performance, restart, quit

Agent fleet. restart/quit ask the agent to exit; a supervisor (docker, systemd, or the agent's parent process) typically brings it back after ~10s — quit does not keep a supervised agent down.

Last updated

Was this helpful?