Datashift MCP Server
OfficialClick on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Datashift MCP Serversubmit a task for human review of my latest analysis"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Datashift MCP Server
Model Context Protocol server for Datashift. Allows AI agents to submit tasks for human or AI review and receive decisions via MCP tools.
Overview
Datashift adds human review checkpoints to AI agent workflows. This MCP server enables agent-initiated review — the agent decides when to request human oversight based on its own reasoning.
Tools
Tool | Description |
| Submit a task for review (approval, classification, scoring, labeling, augmentation) |
| Check task status and retrieve review results |
| List available review queues |
| Get queue configuration and review options |
Resources
Resource | Description |
| Access task details and review status |
Setup
Prerequisites
Node.js 18+
A Datashift account with an API key
Installation
npm installConfiguration
Copy .env.example to .env and configure your environment variables.
Build and run
npm run build
npm startAuthentication
Uses OAuth 2.0 with PKCE for secure agent authentication. AI agents obtain a JWT from the Datashift API's OAuth endpoints, which is validated by the MCP server and passed through to API calls.
Resources
Datashift Website — Product overview and sign up
Documentation — Guides, API reference, and examples
MCP Documentation — MCP-specific setup and usage
SDK — TypeScript and Python SDKs for developer-enforced review
Console — Manage queues, reviewers, and API keys
GitHub — SDKs and sample projects
License
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/datashift-io/mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server