Skip to main content Announcing Tool Policies: AI agent permissions down to the field Read the announcement
Live 3 Actions

Dext MCP Server
for AI Agents

Connect your AI agent to StackOne's Dext MCP server and give it ready-to-use MCP tools out of the box. Auth, tool execution, and security all managed.

Dext logo
Dext MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

3 Agent Actions

Extend your agent's capabilities with custom actions.

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Dext 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 Dext call.

Tools Discovery →

What is the Dext MCP Server?

A Dext MCP server lets AI agents work with Dext data through the Model Context Protocol, Anthropic's open standard for connecting LLMs to external tools. StackOne's Dext MCP server ships with 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 Dext MCP Tools

Every StackOne action for Dext, ready for your agent. Scoped to exactly what you need.

Clients

  • List Clients

    List all practice clients the API token can access, with health score and alert level.

  • Get Client

    Get a practice client's details, including health score, VAT details, debtor metrics and bank reconciliation counts.

Client Activity Stats

  • Get Client Activity Stats

    Get a client's rolling annual, monthly-average and quarterly-average turnover and transaction counts.

Dext AI Agent Use Cases

Connect your AI agent to Dext and help your team scale the finance operations they run by hand today.

Invoice Processing

Automate invoice processing with AI agents connected to your ERP, accounting software, and AP tools through StackOne.

View
QuickBooks OnlineXeroNetSuiteSage IntacctBillFreshBooksWaveZoho Books
Accounts Receivable Dunning

Use StackOne to connect your AI agent to your accounting, CRM, and messaging systems to automate Accounts Receivable dunning and payment follow-up.

View
QuickBooksXeroFreshBooksStripePayPalSalesforceHubSpotGmail
Invoice Processing

Use StackOne to connect your AI agent to your accounting, email, and document management systems to automate invoice processing and purchase order matching.

View
QuickBooks OnlineXeroGmailOutlookGoogle DriveSharePointDropboxSlack

Set Up Your Dext MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Dext 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>"
      ]
    }
  }
}

Check More Accounting MCP Servers

Dext MCP Server FAQ

Does StackOne have a Dext MCP server?
Yes. StackOne offers a hosted Dext MCP server, 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.
Dext MCP server vs direct API integration — what's the difference?
A Dext MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Dext. A Dext 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 Dext at runtime. StackOne provides both.
How does Dext authentication work for AI agents?
Dext 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 Dext account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Dext MCP tools vulnerable to prompt injection?
Yes — Dext 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 Dext agent and how do I avoid it?
Context bloat happens when Dext tool schemas and API responses eat your Dext agent's memory, preventing it from reasoning effectively. A single Dext query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery reduces it by loading only the tools relevant to each query.
Can I limit which actions my Dext agent can access?
Yes — you can limit which actions your Dext 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 Dext MCP server?
Yes — you can create custom agent actions for your Dext MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Dext's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Dext MCP server?
Skip a Dext MCP server if your integration is purely software-to-software — direct Dext 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 Dext actions at runtime.
What AI frameworks and AI clients does the StackOne Dext MCP server support?
The StackOne Dext 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.