Connect
Optimize
Secure
Lattice MCP Server
for AI Agents
Production-ready Lattice MCP server with 34 extensible actions — plus built-in authentication, security, and optimized execution.
Lattice MCP Server
Built by 
StackOne
StackOne 
Coverage
34 Agent Actions
Create, read, update, and delete across Lattice — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Lattice MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Lattice 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 Lattice call.
Tools Discovery →What is the Lattice MCP Server?
A Lattice MCP server lets AI agents read and write Lattice data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Lattice MCP server ships with 34 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 Lattice MCP Tools and Actions
Every action from Lattice's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Departments
- List Departments
Get all departments in the organization
- Get Department
Retrieve detailed information for a specific department by ID
Feedbacks
- List Feedbacks
Get all feedback submissions in the organization
- Get Feedback
Retrieve detailed information for a specific feedback by ID
Goals
- Create Goal
Create a new goal in the organization
- List Goals
Get all goals in the organization
- Get Goal
Retrieve detailed information for a specific goal by ID
- Update Goal
Update an existing goal
Goal Updates
- Create Goal Update
Create a progress update for a specific goal
- List Goal Updates
Get all goal updates across all goals in the organization
- Get Goal Updates
Get all progress updates for a specific goal
Review Cycles
- List Review Cycles
Get all review cycles in the organization
- Get Review Cycle
Retrieve detailed information for a specific review cycle by ID
Tags
- List Tags
Get all tags in the organization
- Get Tag
Retrieve detailed information for a specific tag by ID
Users
- List Users
Get all users in the organization
- Get User
Retrieve detailed information for a specific user by ID
Other (17)
- Get Competency
Retrieve detailed information for a specific competency by ID
- Get Custom Attribute
Retrieve detailed information for a specific custom attribute by ID
- Get Custom Attribute Value
Retrieve a specific custom attribute value by ID
- Get Question
Retrieve a review question by ID
- Get Question Revision
Retrieve a question revision by ID
- List Review Cycle Reviewees
Get all reviewees for a specific review cycle
- List Review Cycle Reviews
Get all reviews for a specific review cycle
- Get Reviewee
Retrieve detailed information for a specific reviewee by ID
- Get Reviewee Reviews
Get all reviews for a specific reviewee
- Get Task
Retrieve a task by ID
- List Updates
Get all updates in the organization
- Get Update
Retrieve detailed information for a specific update by ID
- Get Me
Get the current authenticated user's information
- Get User Direct Reports
Get all direct reports for a specific user
- Get User Custom Attributes
Get all custom attributes for a specific user
- Get User Tasks
Get all tasks for a specific user
- Get User Goals
Get all goals for a specific user
Set Up Your Lattice MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Lattice in under 10 lines of code.
MCP Clients
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>"
]
}
}
}More HRIS / HCM MCP Servers
UKG Ready
140+ actions
Workday (Rest and Soap)
128+ actions
Factorial
127+ actions
HiBob
123+ actions
Oracle Fusion HCM
120+ actions
Humaans
117+ actions
BambooHR
100+ actions
Lattice 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
Lattice MCP Server FAQ
Lattice MCP server vs direct API integration — what's the difference?
A Lattice MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Lattice. A Lattice 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 Lattice at runtime. StackOne provides both.
How does Lattice authentication work for AI agents?
Lattice 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 Lattice account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Lattice MCP tools vulnerable to prompt injection?
Yes — Lattice 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 Lattice agent and how do I avoid it?
Context bloat happens when Lattice tool schemas and API responses eat your Lattice agent's memory, preventing it from reasoning effectively. A single Lattice 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 Lattice agent can access?
Yes — you can limit which actions your Lattice 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 Lattice MCP server?
Yes — you can create custom agent actions for your Lattice MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Lattice's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Lattice MCP server?
Skip a Lattice MCP server if your integration is purely software-to-software — direct Lattice 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 Lattice actions at runtime.
What AI frameworks and AI clients does the StackOne Lattice MCP server support?
The StackOne Lattice 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.