Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →

Live 60 Actions

SmartAdvocate MCP Server
for AI Agents

Connect your AI agent to StackOne's SmartAdvocate MCP server and give it 60 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
SmartAdvocate logo
SmartAdvocate MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

60 Agent Actions

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

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every SmartAdvocate 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 SmartAdvocate call.

Tools Discovery →

What is the SmartAdvocate MCP Server?

A SmartAdvocate MCP server lets AI agents read and write SmartAdvocate data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's SmartAdvocate MCP server ships with 60 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 SmartAdvocate MCP Tools

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

Case Contacts

  • Add Case Contact

    Add a contact to a case

  • Get Case Contacts

    Get all contacts associated with a case

  • Update Case Contact

    Partially update a contact on a case using JSON Patch operations array [{op, path, value}]. Use get_case_contacts first to get contactId

  • Remove Case Contact

    Remove a contact from a case

Contacts

  • Create Contact

    Create a new contact. Set contactCtg to 1 for individual or 2 for organization. Use contact_types to find valid contactTypeId values

  • Get Contact

    Get basic contact info by contact ID

  • Update Contact

    Partially update a contact using JSON Patch operations array [{op, path, value}]. Use contact_info first to get the contactId

Case Notes

  • Create Case Note

    Create a new case note. Requires caseID, noteTypeID (a system-defined note type identifier), and noteText (supports HTML)

  • Get Case Notes

    Get all notes for a case by case ID

  • Get Case Note

    Get a single case note by ID

  • Update Case Note

    Update a case note (full replacement)

Documents

  • Create Document

    Create a document metadata record

  • Get Document

    Get document metadata by ID

  • Download Document

    Download document content as base64

  • Update Document

    Fully update a document metadata record

Tasks

  • Create Task

    Create a new task

  • Get Task

    Get a single task by ID

  • Update Task

    Fully update a task

  • Delete Task

    Delete a task by ID

Users

  • Create User

    Create a new user

  • List Users

    Get all users with basic profile info (ID, name, username, email, status)

  • Get User

    Get a single user by ID

  • Update User

    Fully update a user

  • Delete User

    Delete a user by ID

Other (36)

  • Create Case

    Create a new case

  • Create Appointment

    Create a new calendar appointment for a case

  • Upload Document Content

    Upload file content to an existing document record

  • Create Case Status

    Insert a new case status entry. Requires caseID and statusTypeID (a system-defined status type identifier)

  • Get Case By Number

    Look up a case using its case number string (e.g., 9000002). Use this when you have the case number, not the internal numeric ID

  • Get Case By ID

    Get case by internal case ID

  • Get Active Cases

    List only currently active (open) cases with pagination

  • Get Case Types

    Get case types available within a specific case group. Requires the CaseGroup ID as input

  • Get Case Calendar

    Get all calendar appointments for a case by case ID

  • Get Appointment Types

    Get available appointment types

  • Get Full Contact Info

    Get full contact info including addresses, phones, and emails

  • Get Contact Types

    Get available contact types

  • Get Case Documents

    Get all documents belonging to a specific case by its case ID

  • Get Document Categories

    Get available document categories

  • Get Document Tags

    Get available document tags

  • Get Case Tasks

    Get all tasks for a case by case ID

  • Get Task Types

    Get available task types

  • Get Task Statuses

    Get available task statuses

  • Get Task Priorities

    Get available task priorities

  • List Users (Full Details)

    Get all users with full details

  • Get Case Roles

    Get available case roles

  • Get Firm Roles

    Get available firm roles

  • Get Titles

    Get available user titles

  • Get Offices

    Get available offices

  • Get Departments

    Get available departments

  • Get Permission Groups

    Get available permission groups

  • Get Teams

    Get available teams

  • Get Case Status History

    Get case status history by case ID

  • Get Status Entry

    Get a specific case status entry

  • Get Case Calls

    Get all calls for a case

  • Filter Cases

    Search all cases (open and closed) by modification date range with pagination

  • Filter Calendar Appointments

    Search and filter calendar appointments by date range with pagination

  • Filter Contacts

    Search and filter contacts by date range with pagination

  • Filter Documents

    Search documents across all cases by modification date range with pagination

  • Filter Tasks

    Search and filter tasks by date range with pagination

  • Terminate Case Status

    Terminate/close a case status entry

Set Up Your SmartAdvocate MCP Server in Minutes

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

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

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>"
      ]
    }
  }
}

Platform 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

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

SmartAdvocate MCP Server FAQ

Does StackOne have a SmartAdvocate MCP server?
Yes. StackOne offers a hosted SmartAdvocate MCP server with 60 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.
SmartAdvocate MCP server vs direct API integration — what's the difference?
A SmartAdvocate MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling SmartAdvocate. A SmartAdvocate 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 SmartAdvocate at runtime. StackOne provides both.
How does SmartAdvocate authentication work for AI agents?
SmartAdvocate 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 SmartAdvocate account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are SmartAdvocate MCP tools vulnerable to prompt injection?
Yes — SmartAdvocate 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 SmartAdvocate agent and how do I avoid it?
Context bloat happens when SmartAdvocate tool schemas and API responses eat your SmartAdvocate agent's memory, preventing it from reasoning effectively. A single SmartAdvocate 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 SmartAdvocate agent can access?
Yes — you can limit which actions your SmartAdvocate 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 SmartAdvocate MCP server?
Yes — you can create custom agent actions for your SmartAdvocate MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research SmartAdvocate's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a SmartAdvocate MCP server?
Skip a SmartAdvocate MCP server if your integration is purely software-to-software — direct SmartAdvocate 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 SmartAdvocate actions at runtime.
What AI frameworks and AI clients does the StackOne SmartAdvocate MCP server support?
The StackOne SmartAdvocate 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