Connect
Optimize
Secure
Brainier MCP Server
for AI Agents
Production-ready Brainier MCP server with 45 extensible actions — plus built-in authentication, security, and optimized execution.
Brainier MCP Server
Built by 
StackOne
StackOne 
Coverage
45 Agent Actions
Create, read, update, and delete across Brainier — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Brainier MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Brainier 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 Brainier call.
Tools Discovery →What is the Brainier MCP Server?
A Brainier MCP server lets AI agents read and write Brainier data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Brainier MCP server ships with 45 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 Brainier MCP Tools and Actions
Every action from Brainier's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Users
- Create User
Create a new user with the information provided (assignment changes may take up to an hour to propagate)
- List Users
Retrieve user information for users that meet filter criteria
- Get User
Retrieve all user information for a given user ID
- Update User
Update a pre-existing user with new information (assignment changes may take up to an hour to propagate)
Groups
- Create Group
Create a new group with the information provided
- List Groups
Retrieve group information for groups that meet filter criteria
- Get Group
Retrieve all group information for a given group ID
- Update Group
Update a pre-existing group with new information provided
Roles
- List Roles
Retrieve role information for roles that meet filter criteria
- Get Role
Retrieve all role information for a given role ID
Learning Objects
- List Learning Objects
Retrieve learning object information for multiple learning objects based on filter criteria
- Get Learning Object
Retrieve all learning object information for a given object ID
Object Access
- Create Object Access
Grant front-end access to a learning object for a user or group (must pass either user_id or group_id, but not both)
- Get Object Access
Retrieve the users and groups who have been granted access to a learning object
- Remove Object Access
Remove front-end access to a learning object for a user or group (must pass either user_id or group_id, but not both)
User Object Records
- Create User Object Record
Create a record for a user/object combination with a status such as Complete or Failed
- Get User Object Records
Retrieve started or completed records in the system, with optional date and filter parameters
- Update User Object Record
Update the status of a user object record (e.g., moving from Started to Complete)
Assignments
- Create Assignment
Create an empty assignment batch (can also create a bookmark or recommendation)
- Get Assignments
Retrieve all assignment batches that the caller has access to
Assigned Users
- Create Assigned User
Add a user to an assignment batch
- Get Assigned Users
Retrieve all user IDs that are part of an assignment (individually or through a group)
- Remove Assigned User
Remove a user from an assignment batch
Assigned Groups
- Create Assigned Group
Add a group to an assignment batch
- Get Assigned Groups
Retrieve all group IDs that are part of an assignment
- Remove Assigned Group
Remove a group from an assignment batch
Assigned Objects
- Create Assigned Object
Add a learning object to an assignment batch
- Get Assigned Objects
Retrieve all learning object IDs that are part of an assignment
- Remove Assigned Object
Remove a learning object from an assignment batch
Bookmarks
- Create Bookmark
Bookmark a learning object for the current user
- Remove Bookmark
Remove a bookmark for a learning object
Other (14)
- Add User To Group
Add a single user to the specified group within the context of a role (assignment changes may take up to an hour to propagate)
- Get Learning Object Comments
Retrieve all comments for a given learning object
- Get Class Schedules
Retrieve all schedule information for a given class object
- Get Form Questions And Answers
Retrieve all questions and possible answers for a quiz or survey
- Get Form Options
Retrieve additional configuration options for a quiz or survey set in the Brainier LMS backend
- Get User Form Answers
Retrieve answers provided by a user for all questions in a quiz or survey for a single record
- Get Assignments By User
Retrieve all assigned objects and assignment information for a particular user
- Get Tags
Retrieve all system tags or tags associated with objects the user has access to
- Get Bookmarked Objects
Retrieve all learning objects that the caller has bookmarked
- Get Object Authors
Retrieve all authors associated with a learning object
- Get All Object Authors
Retrieve all authors the caller has access to (associated with accessible objects)
- Get Objects By Author
Retrieve all learning objects that have the specified user or faculty as an author
- Remove User From Group
Remove a single user from a group (assignment changes may take up to an hour to propagate)
- Unregister From Class
Delete a user object record to unregister a user from a class (only works for class objects)
Set Up Your Brainier MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Brainier 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 Learning / LMS MCP Servers
Saba
122+ actions
Xyleme
79+ actions
360Learning
78+ actions
Adobe Learning Manager
72+ actions
Go1
69+ actions
SAP SuccessFactors
69+ actions
Discourse
67+ actions
Brainier 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
Brainier MCP Server FAQ
Brainier MCP server vs direct API integration — what's the difference?
A Brainier MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Brainier. A Brainier 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 Brainier at runtime. StackOne provides both.
How does Brainier authentication work for AI agents?
Brainier 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 Brainier account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Brainier MCP tools vulnerable to prompt injection?
Yes — Brainier 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 Brainier agent and how do I avoid it?
Context bloat happens when Brainier tool schemas and API responses eat your Brainier agent's memory, preventing it from reasoning effectively. A single Brainier 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 Brainier agent can access?
Yes — you can limit which actions your Brainier 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 Brainier MCP server?
Yes — you can create custom agent actions for your Brainier MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Brainier's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Brainier MCP server?
Skip a Brainier MCP server if your integration is purely software-to-software — direct Brainier 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 Brainier actions at runtime.
What AI frameworks and AI clients does the StackOne Brainier MCP server support?
The StackOne Brainier 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.