Connect
Optimize
Secure
Aha! MCP Server
for AI Agents
Production-ready Aha! MCP server with 78 extensible actions — plus built-in authentication, security, and optimized execution.
Aha! MCP Server
Built by 
StackOne
StackOne 
Coverage
78 Agent Actions
Create, read, update, and delete across Aha! — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Aha! MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Aha! 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 Aha! call.
Tools Discovery →What is the Aha! MCP Server?
A Aha! MCP server lets AI agents read and write Aha! data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Aha! MCP server ships with 78 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 Aha! MCP Tools and Actions
Every action from Aha!'s API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Comments
- Update Comment
Update an existing comment
- Delete Comment
Delete a comment
Epics
- Create Epic
Create a new epic
- List Epics
List all epics
- Get Epic
Get specific epic by ID or key
- Update Epic
Update an existing epic
- Delete Epic
Delete an epic
Features
- Create Feature
Create a new feature
- List Features
List all features
- Get Feature
Get specific feature by ID or key
- Update Feature
Update an existing feature
- Delete Feature
Delete a feature
Goals
- Create Goal
Create a new goal
- List Goals
List all goals
- Get Goal
Get specific goal by ID
- Update Goal
Update an existing goal
- Delete Goal
Delete a goal
Ideas
- Create Idea
Create a new idea
- List Ideas
List all ideas
- Get Idea
Get specific idea by ID or key
- Update Idea
Update an existing idea
- Delete Idea
Delete an idea
Initiatives
- Create Initiative
Create a new initiative
- List Initiatives
List all initiatives
- Get Initiative
Get specific initiative by ID or key
- Update Initiative
Update an existing initiative
- Delete Initiative
Delete an initiative
Products
- Create Product
Create a new product
- List Products
List all products in the account
- Get Product
Get specific product by ID or key
- Update Product
Update an existing product
Releases
- Create Release
Create a new release
- Get Release
Get specific release by ID or key
- Update Release
Update an existing release
- Delete Release
Delete a release
Requirements
- Create Requirement
Create a new requirement
- Get Requirement
Get specific requirement by ID
- Update Requirement
Update an existing requirement
- Delete Requirement
Delete a requirement
Tasks
- Create Task
Create a new task
- List Tasks
List all to-dos
- Get Task
Get specific task by ID
- Update Task
Update an existing task
- Delete Task
Delete a task
Approvals
- Create Approval
Create a new approval
- List Approvals
List all approval tasks
Users
- Create User
Create a new user in a product
- List Users
List all users in the account
- Get User
Get specific user by ID
- Update User
Update an existing user
Other (28)
- Create Comment For Feature
Add a comment to a feature
- Create Comment For Epic
Add a comment to an epic
- List Comments For Feature
List comments on a feature
- List Comments For Epic
List comments on an epic
- List Epics In Product
List epics in a specific product
- List Features In Release
List features in a specific release
- List Features In Product
List features in a specific product
- List Features In Epic
List features in a specific epic
- List Goals In Product
List goals in a specific product
- List Ideas In Product
List ideas for a specific product
- List Initiatives In Product
List initiatives in a specific product
- List Releases Associated With Goal
List releases associated with a goal
- List Releases Associated With Initiative
List releases associated with an initiative
- List Releases In Product
List releases in a specific product
- List Requirements For Feature
List requirements for a feature
- List Tasks For Feature
List tasks associated with a feature
- Get Current User
Retrieve the current user profile information
- List User's Product Roles
List a user's product roles
- Update Epic Tags
Update tags for an epic
- Update Epic Progress
Update progress percentage for an epic
- Update Feature Tags
Update tags for a feature
- Move Feature To Release
Move a feature to a different release
- Update Goal Progress
Update progress for a goal
- Update Release Progress
Update progress percentage for a release
- Update Task Status
Update a task's status
- Update Approval Status
Update an approval's status
- Delete User Product Role
Delete a user's product role
- Promote Idea
Promote an idea to feature, epic, initiative, or requirement
Set Up Your Aha! MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Aha! 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 Project Management MCP Servers
Azure DevOps
172+ actions
Bitbucket
134+ actions
Jira
134+ actions
Confluence
133+ actions
Trello
133+ actions
Asana
126+ actions
GitLab
125+ actions
Aha! 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
Aha! MCP Server FAQ
Aha! MCP server vs direct API integration — what's the difference?
A Aha! MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Aha!. A Aha! 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 Aha! at runtime. StackOne provides both.
How does Aha! authentication work for AI agents?
Aha! 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 Aha! account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Aha! MCP tools vulnerable to prompt injection?
Yes — Aha! 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 Aha! agent and how do I avoid it?
Context bloat happens when Aha! tool schemas and API responses eat your Aha! agent's memory, preventing it from reasoning effectively. A single Aha! 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 Aha! agent can access?
Yes — you can limit which actions your Aha! 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 Aha! MCP server?
Yes — you can create custom agent actions for your Aha! MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Aha!'s API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Aha! MCP server?
Skip a Aha! MCP server if your integration is purely software-to-software — direct Aha! 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 Aha! actions at runtime.
What AI frameworks and AI clients does the StackOne Aha! MCP server support?
The StackOne Aha! 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.