About Integrate.io MCP Server
Integrate.io MCP Server lets AI clients build, run, and monitor Integrate.io ETL and Reverse ETL pipelines using natural-language requests. It is for teams managing data pipelines in Integrate.io and offers tools for inspection, editing, jobs, and schedules.
Key features
- 01Inspect connections, packages, and runs
- 02Discover schemas and profile data
- 03Build and edit pipeline packages
- 04Run, retry, or cancel jobs
- 05Diagnose failures and manage schedules
Use cases
- 01Review pipeline runs and preview data
- 02Create a pipeline from a description
- 03Revise a package or roll back a version
- 04Investigate failed jobs and adjust schedules
MCP support
It exposes 44 tools to MCP clients for reading, building, and managing Integrate.io pipelines and jobs. Clients connect to the account's remote MCP server URL and authenticate with OAuth or a Personal Access Token.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.xplenty.com/{account}/api/mcpclaude mcp add --transport http xplenty-integrateio https://api.xplenty.com/{account}/api/mcp{"mcpServers":{"xplenty-integrateio":{"type":"http","url":"https://api.xplenty.com/{account}/api/mcp"}}}Open in Cursor{"servers":{"xplenty-integrateio":{"type":"http","url":"https://api.xplenty.com/{account}/api/mcp"}}}Open in VS Code{"mcpServers":{"xplenty-integrateio":{"type":"http","url":"https://api.xplenty.com/{account}/api/mcp"}}}{"mcpServers":{"xplenty-integrateio":{"serverUrl":"https://api.xplenty.com/{account}/api/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 READMEIntegrate.io MCP Server
The official MCP server for Integrate.io ETL and Reverse ETL. Connect Claude, ChatGPT, Cursor, OpenAI Codex or any MCP-compatible AI client to your Integrate.io account and build, run and monitor data pipelines in plain language.
Integrate.io was formerly called Xplenty. Our API domain (api.xplenty.com) and this GitHub organization still use the old name.
- Product page: https://www.integrate.io/platform/mcp/
- Documentation: https://www.integrate.io/docs/etl/integrateio-mcp-server
Connect
- Copy your MCP server URL from Settings → Developer Settings → Connected Applications in the Integrate.io dashboard. It looks like https://api.xplenty.com/YOUR_ACCOUNT/api/mcp
- Add it to your AI client as a remote MCP server and sign in with OAuth. Clients without OAuth support use a Personal Access Token, and stdio-only clients (Claude Desktop, Cursor, Codex) use the mcp-remote bridge. The docs have a ready-to-paste config for each.
Step-by-step setup for claude.ai, Claude Desktop, Claude Code, ChatGPT, Cursor and OpenAI Codex: https://www.integrate.io/docs/etl/integrateio-mcp-server
What it can do
44 tools in three groups:
| Group | Examples |
|---|---|
| Reading and inspecting | List connections, packages and runs; discover schemas; preview and profile data |
| Building and editing | Build a pipeline from a description; clone and edit packages; roll back versions |
| Jobs and schedules | Run, cancel and retry jobs; diagnose failures; manage schedules |
Full reference: https://www.integrate.io/docs/etl/integrateio-mcp-server#tool-reference
Security
- Actions follow the same roles and permissions as the Integrate.io app
- Every change made through MCP is recorded in the account's audit history
- Package edits are versioned and can be rolled back
- Access can be revoked at any time from Connected Applications
- Credentials, TLS certificates and SSL keys are never returned
Support and privacy
- Support: https://www.integrate.io/support/
- Privacy policy: https://www.integrate.io/privacy/
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.