Connect
Optimize
Secure
Live 30 Actions
Moss MCP Server
for AI Agents
Connect your AI agent to StackOne's Moss MCP server and give it 30 MCP tools out of the box. Auth, tool execution, and security all managed.
Moss MCP Server
Built by 
StackOne
StackOne 
Coverage
30 Agent Actions
Create, read, update, and delete across Moss — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Moss MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Moss 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 Moss call.
Tools Discovery →What is the Moss MCP Server?
A Moss MCP server lets AI agents read and write Moss data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Moss MCP server ships with 30 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 Moss MCP Tools
Every action from Moss's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Expenses
- List Expenses
Returns a paginated list of expenses with optional filtering by type, status, export status, and date ranges
Expense Accounts
- List Expense Accounts
Returns a paginated list of expense accounts with optional filtering and sorting
- Get Expense Account
Returns expense account information for a specific expense account ID
Dimensions
- Create Dimension
Creates a new dimension in the accounting system
- List Dimensions
Returns all dimensions within the authenticated user's organization
- Get Dimension
Returns dimension information for a specific dimension ID
- Update Dimension
Updates an existing dimension in the accounting system
Dimension Items
- Create Dimension Item
Creates a new dimension item for the specified dimension
- List Dimension Items
Returns a paginated list of dimension items with optional filtering and sorting
- Get Dimension Item
Returns dimension item information for a specific dimension item ID
- Update Dimension Item
Updates an existing dimension item
Suppliers
- Create Supplier
Creates a new supplier in the authenticated user's organization
- List Suppliers
Returns a paginated list of suppliers with optional filtering and sorting
- Get Supplier
Returns supplier information for a specific supplier ID
- Update Supplier
Partially updates a supplier in the authenticated user's organization
Payment Terms
- List Payment Terms
Returns a paginated list of payment terms with optional filtering and sorting
- Get Payment Term
Returns payment term information for a specific payment term ID
Tax Rates
- List Tax Rates
Returns a paginated list of tax rates with optional filtering and sorting
- Get Tax Rate
Returns tax rate information for a specific tax rate ID
Users
- List Users
Returns a paginated list of users with optional filtering and sorting
- Get User
Returns user information for a specific user ID
Teams
- List Teams
Returns a paginated list of teams with optional filtering and sorting
- Get Team
Returns team information for a specific team ID
Departments
- List Departments
Returns a paginated list of departments with optional filtering and sorting
- Get Department
Returns department information for a specific department ID
Bank Accounts
- List Bank Accounts
Returns all bank accounts (wallets) for the authenticated user's organization
Bank Account Balances
- Get Bank Account Balance
Returns the current balance for a specific bank account
Bank Transactions
- Search Bank Transactions
Returns a paginated list of bank transactions for a specific bank account within a date range
Files
- Search Files
Returns a paginated list of files based on expense IDs
- Download File
Downloads file contents by its ID
Set Up Your Moss MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Moss in under 10 lines of code.
Agent Frameworks
JSON{
"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
Moss MCP Server FAQ
Does StackOne have a Moss MCP server?
Yes. StackOne offers a hosted Moss MCP server with 30 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.
Moss MCP server vs direct API integration — what's the difference?
A Moss MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Moss. A Moss 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 Moss at runtime. StackOne provides both.
How does Moss authentication work for AI agents?
Moss 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 Moss account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Moss MCP tools vulnerable to prompt injection?
Yes — Moss 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 Moss agent and how do I avoid it?
Context bloat happens when Moss tool schemas and API responses eat your Moss agent's memory, preventing it from reasoning effectively. A single Moss 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 Moss agent can access?
Yes — you can limit which actions your Moss 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 Moss MCP server?
Yes — you can create custom agent actions for your Moss MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Moss's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Moss MCP server?
Skip a Moss MCP server if your integration is purely software-to-software — direct Moss 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 Moss actions at runtime.
What AI frameworks and AI clients does the StackOne Moss MCP server support?
The StackOne Moss 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.