generateBacklogLABSCO SUMMARY
The output is a directory of files, not a chat response.
Writing the backlog to disk as annotated Markdown is what separates this from asking a model to draft user stories: the result lands in the repository where the implementing assistant will read it, with checkboxes it can tick. The schema validation step matters too — a backlog that fails structure checks is regenerated rather than written half-formed. MCP_EXECUTION is the setting people miss.
What it is
An MCP server that generates agile backlogs through an LLM and writes them to disk as a structured directory of Markdown files. Output goes into a .agile-planner-backlog folder with epics containing features containing user stories, plus an orphan-stories folder for anything not attached to a feature and a backlog.json alongside. Every generated file carries annotations aimed at the AI assistant that will implement the work.
What you get
generateBacklog— a complete backlog from aprojectNameand aprojectDescription, with an optionaloutputPathgenerateFeature— one feature from afeatureDescription, with an optionalstoryCountof at least 3, abusinessValue, aniterationName, anepicNameto attach it to or let the system pick, and anoutputPath- A validation pipeline rather than raw generation: the structure is checked against a JSON schema, features are enriched with acceptance criteria and tasks, and stories are organised into epics and features before any file is written
- Task checkboxes for progress tracking and dependency notes in the generated files
- The same two operations available as a CLI, so a backlog can be generated outside an editor
- Uniform error handling — every failure from the backlog functions returns the same JSON shape rather than an ad-hoc message
Requirements
An LLM key: OPENAI_API_KEY or GROQ_API_KEY as the alternative. MCP_EXECUTION must be set to "true" for MCP mode — the server will not behave correctly without it. Node.js; the package is agile-planner-mcp-server (1.7.3 in package.json) and the documented client entry runs npx agile-planner-mcp-server, or node against server/index.js for a local checkout. AGILE_PLANNER_OUTPUT_ROOT sets the base output directory, and TEST_MODE produces mock output without calling a model.
Setup effort
One command plus a key — npx agile-planner-mcp-server, then supply credentials
USE CASES
01
Getting from an idea to a working backlog
Describe the project in a paragraph and receive epics, features and stories as files in the repository.
02
Adding one feature to an existing plan
Generate a single feature with a chosen story count and let it attach to the right epic.
03
Handing work to a coding assistant
Point the assistant at the generated Markdown, where each story already carries acceptance criteria, tasks and checkboxes.
04
Trying it without spending on a model
Run in test mode to see the directory structure and file shape before wiring in a real key.
3 tools
Listed in project docs. Your client may show a different list.
generateFeaturegetStatusBEFORE YOU INSTALL
What to know first
Tools you get
3 tools named in the project's documentation.
Requires
- npx on PATH
- OPENAI_API_KEY or GROQ_API_KEY in your environment
INSTALLATION
Connect your client
Server setup
TERMINAL
npx agile-planner-mcp-serverMCP Clients
Windsurf
WINDSURF · JSON
{
"mcpServers": {
"agile-planner": {
"command": "npx",
"args": [
"agile-planner-mcp-server"
],
"env": {
"MCP_EXECUTION": "true",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}The configuration on this page does not set GROQ_API_KEY; the project's instructions put it in a .env file. To supply GROQ_API_KEY without depending on where the server looks for that file, use the block's "env" section.
Any MCP client — local install
Clone the repository and install its dependencies
Needs Node.js and npm.
ANY MCP CLIENT — LOCAL INSTALL · TERMINAL
git clone https://github.com/cyberlife-coder/agile-planner-mcp-server.git
cd agile-planner-mcp-server
npm installAdd this to your client's MCP configuration
<YOUR_PATH_TO_AGILE_PLANNER_MCP_SERVER> is the folder you cloned into. To use Groq, set GROQ_API_KEY instead of OPENAI_API_KEY.
ANY MCP CLIENT — LOCAL INSTALL · JSON
{
"mcpServers": {
"agile-planner": {
"command": "node",
"args": [
"<YOUR_PATH_TO_AGILE_PLANNER_MCP_SERVER>/server/index.js"
],
"env": {
"MCP_EXECUTION": "true",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}The configuration on this page does not set GROQ_API_KEY; the project's instructions put it in a .env file. To supply GROQ_API_KEY without depending on where the server looks for that file, use the block's "env" section.
