Skip to main content Announcing Tool Gateway MCP: the universal MCP Read the announcement
Live 32 Actions

Magnit Gateway MCP Server
for AI Agents

Connect your AI agent to StackOne's Magnit Gateway MCP server and give it 32 MCP tools out of the box. Auth, tool execution, and security all managed.

Magnit Gateway logo
Magnit Gateway MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

32 Agent Actions

Create, read, update, and delete across Magnit Gateway — and extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Magnit Gateway MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Magnit Gateway tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Magnit Gateway call.

Tools Discovery →

What is the Magnit Gateway MCP Server?

A Magnit Gateway MCP server lets AI agents read and write Magnit Gateway data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Magnit Gateway MCP server ships with 32 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Magnit Gateway MCP Tools

Every action from Magnit Gateway's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Staffing Engagements

  • List Staffing Engagements

    List staffing engagements (worker assignments)

  • Get Staffing Engagement

    Get details of a staffing engagement

SOW Requests

  • List SOW Requests

    List SOW (project) requests released to the supplier

  • Get SOW Request

    Get full details of a SOW (project) request

Webhook Subscriptions

  • Create Webhook Subscription

    Create a webhook subscription for Magnit event notifications

  • List Webhook Subscriptions

    List webhook subscriptions registered by the calling credentials

  • Update Webhook Subscription

    Update the callback URL, active state, or failure email of a webhook subscription

Workers

  • Create Worker

    Create a worker profile for future submittals

  • List Workers

    List worker profiles in the supplier population

  • Update Worker

    Update an existing worker profile

Other (22)

  • Create Or Modify Timecard

    Submit or modify a timecard for a staffing engagement

  • Upload Worker Attachment (Multipart)

    Upload a supporting document to a worker profile (multipart)

  • Upload Worker Attachment (Base64)

    Upload a supporting document to a worker profile (base64)

  • List Billing Items

    List billing items with timesheet, expense, adjustment and SOW details

  • List Invoices

    List invoice details at the billing item level

  • List Clients With Op Units

    List contracted Magnit clients and their Op Units

  • List Client Custom Fields

    List client custom fields required for candidate submission

  • Get Custom Field Reference List

    Get the values of a custom field dropdown reference list

  • List Custom Candidate Submission Requirements

    Get candidate submission requirements for an Op Unit and country

  • List Gateway Suppliers

    List supplier records in the Gateway group subscription

  • Get SOW Request Attachment

    Download a SOW request attachment file

  • List SOW Quote Submission Statuses

    List the status of submitted SOW quotes

  • List Staffing Requests

    List staffing requests released to the supplier for sourcing

  • List Candidate Submission Statuses

    List the status of submitted candidates on staffing requests

  • Get Staffing Request Attachment

    Download a staffing request attachment file

  • Download Worker Resume

    Download a worker resume file

  • Update Candidate Submission

    Update an existing candidate submission

  • Update Webhook Subscription Events

    Add or remove event types on a webhook subscription

  • Submit Candidate (Multipart)

    Submit a candidate to a request with a multipart resume upload

  • Submit Candidate (Base64)

    Submit a candidate to a request with a base64 resume

  • Withdraw Candidate Submission

    Withdraw a candidate submission from a request

  • Generate Pre-Submittal Insights

    Generate a Maggi match score and insights before submitting a candidate

Set Up Your Magnit Gateway MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Magnit Gateway in under 10 lines of code.

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Magnit Gateway MCP Server FAQ

Does StackOne have a Magnit Gateway MCP server?
Yes. StackOne offers a hosted Magnit Gateway MCP server with 32 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Magnit Gateway MCP server vs direct API integration — what's the difference?
A Magnit Gateway MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Magnit Gateway. A Magnit Gateway MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Magnit Gateway at runtime. StackOne provides both.
How does Magnit Gateway authentication work for AI agents?
Magnit Gateway authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Magnit Gateway account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Magnit Gateway MCP tools vulnerable to prompt injection?
Yes — Magnit Gateway MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Magnit Gateway agent and how do I avoid it?
Context bloat happens when Magnit Gateway tool schemas and API responses eat your Magnit Gateway agent's memory, preventing it from reasoning effectively. A single Magnit Gateway query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Magnit Gateway agent can access?
Yes — you can limit which actions your Magnit Gateway agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Magnit Gateway MCP server?
Yes — you can create custom agent actions for your Magnit Gateway MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Magnit Gateway's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Magnit Gateway MCP server?
Skip a Magnit Gateway MCP server if your integration is purely software-to-software — direct Magnit Gateway API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Magnit Gateway actions at runtime.
What AI frameworks and AI clients does the StackOne Magnit Gateway MCP server support?
The StackOne Magnit Gateway MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.