Dixa MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Dixa MCP server support?

The StackOne Dixa 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.

Production-ready Dixa MCP server with 65 extensible actions — plus built-in authentication, security, and optimized execution.

Start Free Book Demo Read Docs →

Dixa MCP Server

Built by

StackOne

Coverage

65 Agent Actions

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

MCP Actions → Create Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Dixa 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 Dixa call.

Tools Discovery →

What is the Dixa MCP Server?

A Dixa MCP server lets AI agents read and write Dixa data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Dixa MCP server ships with 65 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Dixa MCP Tools and Actions

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

Agents

Create Agent
Create a new agent
List Agents
List all agents and admins in the organization
Get Agent
Get an agent or admin by ID
Delete Agent
Delete an agent or admin

Contact Endpoints

List Contact Endpoints
List all contact endpoints in the organization
Get Contact Endpoint
Get a contact endpoint by ID

Conversations

Create Conversation
Create a new conversation
Get Conversation
Get a conversation by ID
Search Conversations
Search for conversations with filters

Conversation Messages

Add Conversation Message
Add a message to a conversation
List Conversation Messages
Get all messages for a conversation

Conversation Internal Notes

Add Conversation Internal Note
Add an internal note to a conversation
List Conversation Internal Notes
Get all internal notes for a conversation

Custom Attributes

List Custom Attributes
List all custom attribute definitions
Get Custom Attribute
Get a custom attribute definition by ID

End Users

Create End User
Create a new end user
List End Users
List all end users in the organization
Get End User
Get an end user by ID

Queues

Create Queue
Create a new queue
List Queues
List all queues in the organization
Get Queue
Get a queue by ID

Teams

Create Team
Create a new team
List Teams
List all teams in the organization
Get Team
Get a team by ID
Delete Team
Delete a team

Team Members

Add Team Members
Add members to a team
List Team Members
List all members of a team
Remove Team Members
Remove members from a team

Webhooks

Create Webhook
Create a new webhook subscription
List Webhooks
List all webhook subscriptions
Get Webhook
Get a webhook subscription by ID
Delete Webhook
Delete a webhook subscription

Other (29)

Create Rating Offer
Create a rating offer for a conversation
Get Agent Presence
Get the presence status for an agent or admin
List Agents Presence
List presence status for all agents
List Agent Teams
List teams that an agent belongs to
List Conversation Tags
Get all tags for a conversation
List Conversation Ratings
List ratings for a conversation
List Conversation Flows
List all conversation flows in an organization
List End User Conversations
List conversations requested by an end user
List Knowledge Collections
List all knowledge base collections
Get Knowledge Article
Get a knowledge base article by ID
Get Organization
Get organization details associated with the API token
List Queue Members
List all agents/admins that are members of a queue
List Templates
List all templates in the organization
Patch Agent
Partially update an agent or admin
Close Conversation
Mark a conversation as closed
Reopen Conversation
Reopen a closed conversation
Followup Conversation
Follow up a conversation with expiration timestamp
Transfer Conversation To Queue
Transfer a conversation to a target queue
Claim Conversation
Claim a conversation for a given agent
Anonymize Conversation
Request the anonymization of a conversation
Tag Conversation
Add a tag to a conversation
Untag Conversation
Remove a tag from a conversation
Submit Rating Result
Submit a rating result for a conversation
Patch Conversation Custom Attributes
Patch custom attributes of a conversation
Patch End User
Partially update an end user
Anonymize End User
Request the anonymization of an end user
Patch End User Custom Attributes
Patch custom attributes of an end user
Assign Agents To Queue
Assign agents/admins to a queue
Patch Webhook
Patch a webhook subscription

Set Up Your Dixa MCP Server in Minutes

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

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Docs

{
  "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>"
      ]
    }
  }
}

More Customer Support MCP Servers

123+ actions

104+ actions

84+ actions

74+ actions

71+ actions

69+ actions

67+ actions

All Customer Support MCP Servers →

Dixa MCP Server Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

Dixa MCP Server FAQ

Dixa MCP server vs direct API integration — what's the difference?

A Dixa MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Dixa. A Dixa 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 Dixa at runtime. StackOne provides both.

How does Dixa authentication work for AI agents?

Dixa 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 Dixa account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Dixa MCP tools vulnerable to prompt injection?

Yes — Dixa 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 Dixa agent and how do I avoid it?

Context bloat happens when Dixa tool schemas and API responses eat your Dixa agent's memory, preventing it from reasoning effectively. A single Dixa 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 Dixa agent can access?

Yes — you can limit which actions your Dixa 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 Dixa MCP server?

Yes — you can create custom agent actions for your Dixa MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Dixa's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Dixa MCP server?

Skip a Dixa MCP server if your integration is purely software-to-software — direct Dixa 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 Dixa actions at runtime.

What AI frameworks and AI clients does the StackOne Dixa MCP server support?

The StackOne Dixa 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.

Start Free Book Demo

Dixa MCP Serverfor AI Agents