Live 72 Actions

Rally MCP Server
for AI Agents

Q: What AI frameworks and AI clients does the StackOne Rally MCP server support?

The StackOne Rally 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.

Connect your AI agent to StackOne's Rally MCP server and give it 72 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Rally MCP Server

Built by

StackOne

Coverage

72 Agent Actions

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

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

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

Agent Auth →

Security

Agent Protection

Every Rally 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 Rally call.

Tools Discovery →

What is the Rally MCP Server?

A Rally MCP server lets AI agents read and write Rally data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Rally MCP server ships with 72 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 Rally MCP Tools

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

User Storys

Create User Story
Create a new user story in Rally
Get User Story
Get a single user story by ObjectID
Update User Story
Update an existing user story in Rally
Delete User Story
Delete a user story from Rally

Defects

Create Defect
Create a new defect in Rally
List Defects
List all defects in Rally
Get Defect
Get a single defect by ObjectID
Update Defect
Update an existing defect in Rally
Delete Defect
Delete a defect from Rally

Tasks

Create Task
Create a new task in Rally
List Tasks
List all tasks in Rally
Get Task
Get a single task by ObjectID
Update Task
Update an existing task in Rally
Delete Task
Delete a task from Rally

Test Cases

Create Test Case
Create a new test case in Rally
List Test Cases
List all test cases in Rally
Get Test Case
Get a single test case by ObjectID
Update Test Case
Update an existing test case in Rally
Delete Test Case
Delete a test case from Rally

Features

Create Feature
Create a new portfolio item feature in Rally
List Features
List all portfolio item features in Rally
Get Feature
Get a single portfolio item feature by ObjectID
Update Feature
Update an existing feature in Rally
Delete Feature
Delete a feature from Rally

Initiatives

Create Initiative
Create a new portfolio item initiative in Rally
List Initiatives
List all portfolio item initiatives in Rally
Get Initiative
Get a single portfolio item initiative by ObjectID
Update Initiative
Update an existing initiative in Rally

Projects

Create Project
Create a new project in Rally
List Projects
List all projects in Rally
Get Project
Get a single project by ObjectID
Update Project
Update an existing project in Rally

Workspaces

Create Workspace
Create a new workspace in Rally
List Workspaces
List all workspaces in Rally
Get Workspace
Get a single workspace by ObjectID
Update Workspace
Update an existing workspace in Rally

Iterations

Create Iteration
Create a new iteration (sprint) in Rally
List Iterations
List all iterations (sprints) in Rally
Get Iteration
Get a single iteration by ObjectID
Update Iteration
Update an existing iteration in Rally
Delete Iteration
Delete an iteration from Rally

Releases

Create Release
Create a new release in Rally
List Releases
List all releases in Rally
Get Release
Get a single release by ObjectID
Update Release
Update an existing release in Rally
Delete Release
Delete a release from Rally

Milestones

Create Milestone
Create a new milestone in Rally
List Milestones
List all milestones in Rally
Get Milestone
Get a single milestone by ObjectID
Update Milestone
Update an existing milestone in Rally
Delete Milestone
Delete a milestone from Rally

Users

Create User
Create a new user in Rally
List Users
List all users in the Rally subscription
Get User
Get a single user by ObjectID
Update User
Update an existing user in Rally
Delete User
Delete a user from Rally

Attachments

Create Attachment
Create a new attachment in Rally
List Attachments
List all attachments in Rally
Get Attachment
Get a single attachment by ObjectID
Update Attachment
Update an existing attachment in Rally
Delete Attachment
Delete an attachment from Rally

Webhooks

List Webhooks
List all webhook subscriptions in Rally
Get Webhook
Get a single webhook subscription by UUID
Update Webhook
Update an existing webhook subscription in Rally
Delete Webhook
Delete a webhook subscription from Rally

Other (2)

List User Stories
List all user stories in Rally
Get Current User
Get the currently authenticated user

Set Up Your Rally MCP Server in Minutes

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

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "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

Rally MCP Server FAQ

Does StackOne have a Rally MCP server?

Yes. StackOne offers a hosted Rally MCP server with 72 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.

Rally MCP server vs direct API integration — what's the difference?

A Rally MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Rally. A Rally 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 Rally at runtime. StackOne provides both.

How does Rally authentication work for AI agents?

Rally 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 Rally account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Rally MCP tools vulnerable to prompt injection?

Yes — Rally 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 Rally agent and how do I avoid it?

Context bloat happens when Rally tool schemas and API responses eat your Rally agent's memory, preventing it from reasoning effectively. A single Rally 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 Rally agent can access?

Yes — you can limit which actions your Rally 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 Rally MCP server?

Yes — you can create custom agent actions for your Rally MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Rally's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Rally MCP server?

Skip a Rally MCP server if your integration is purely software-to-software — direct Rally 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 Rally actions at runtime.

What AI frameworks and AI clients does the StackOne Rally MCP server support?

The StackOne Rally 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

Rally MCP Serverfor AI Agents