Connect
Optimize
Secure
The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →
Connect your AI agent to StackOne's Rally MCP server and give it 68 MCP tools out of the box. Auth, tool execution, and security all managed.
Coverage
Create, read, update, and delete across Rally — and extend your agent's capabilities with custom actions.
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
Every Rally tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →Performance
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Rally call.
Tools Discovery →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 68 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.
Every action from Rally's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Create a new user story in Rally
Get a single user story by ObjectID
Update an existing user story in Rally
Delete a user story from Rally
Create a new defect in Rally
List all defects in Rally
Get a single defect by ObjectID
Update an existing defect in Rally
Delete a defect from Rally
Create a new task in Rally
List all tasks in Rally
Get a single task by ObjectID
Update an existing task in Rally
Delete a task from Rally
Create a new test case in Rally
List all test cases in Rally
Get a single test case by ObjectID
Update an existing test case in Rally
Delete a test case from Rally
Create a new portfolio item feature in Rally
List all portfolio item features in Rally
Get a single portfolio item feature by ObjectID
Update an existing feature in Rally
Delete a feature from Rally
Create a new portfolio item initiative in Rally
List all portfolio item initiatives in Rally
Get a single portfolio item initiative by ObjectID
Update an existing initiative in Rally
Create a new project in Rally
List all projects in Rally
Get a single project by ObjectID
Update an existing project in Rally
Create a new workspace in Rally
List all workspaces in Rally
Get a single workspace by ObjectID
Update an existing workspace in Rally
Create a new iteration (sprint) in Rally
List all iterations (sprints) in Rally
Get a single iteration by ObjectID
Update an existing iteration in Rally
Delete an iteration from Rally
Create a new release in Rally
List all releases in Rally
Get a single release by ObjectID
Update an existing release in Rally
Delete a release from Rally
Create a new milestone in Rally
List all milestones in Rally
Get a single milestone by ObjectID
Update an existing milestone in Rally
Delete a milestone from Rally
Create a new user in Rally
List all users in the Rally subscription
Get a single user by ObjectID
Update an existing user in Rally
Delete a user from Rally
Create a new attachment in Rally
List all attachments in Rally
Get a single attachment by ObjectID
Update an existing attachment in Rally
Delete an attachment from Rally
Create a new tag in Rally
List all tags in Rally
Get a single tag by ObjectID
Update an existing tag in Rally
Delete a tag from Rally
List all user stories in Rally
Get the currently authenticated user
One endpoint. Any framework. Your agent is talking to Rally in under 10 lines of code.
Agent Frameworks
{
"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>"
]
}
}
}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
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
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
origin_owner_id.All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.