@jst-stack/mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@jst-stack/mcpstart a task to add a user profile page to the dashboard"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@jst-stack/mcp
MCP server and Pi extension for JST architecture workflows. It exposes four operations — start a task, scaffold a slice, fetch a recipe, run a quality gate — by delegating to a project's own npm run create:slice, npm run lint:*, and npm run check:* scripts. It duplicates no JST generator, lint, or architecture policy: architecture guidance is read from each project's local skills/frontend-architecture/SKILL.md, and the package embeds only operational mappings (gate-to-script, section selection keywords, CLI-help parsing).
Requirements
Node.js
>= 24.15A JST project (scaffolded with
create-jst) that exposes acreate:slicescript.
Related MCP server: SnapBack
Tools
Tool | Purpose |
| Classify the brief as a direct file/docs change, local UI edit, existing-workflow change, or new boundary; return only its workflow and relevant architecture sections. Generator discovery runs only for a new boundary. |
| Validate kind/name/options and invoke the project-local |
| Return the matching project-local recipe section ( |
| Run an existing npm script ( |
Every response is concise JSON. Raw diagnostic output is truncated; no source files are dumped.
Install: generic MCP clients
npm install -g @jst-stack/mcpAdd a stdio server to your client config, for example:
{
"mcpServers": {
"jst": {
"command": "jst-mcp"
}
}
}Without a global install, configure the executable and arguments separately:
{
"mcpServers": {
"jst": {
"command": "npx",
"args": ["-y", "@jst-stack/mcp"]
}
}
}Agent workflow
Call
jst_start_taskonce with the project root and implementation brief.For a local UI/content/style edit, change only its owner and colocated files. Use
jst_scaffold_sliceonly for a genuinely new architecture boundary.Implement against the returned project-local contract; request a named recipe only when the start response did not include it.
Run focused tests while implementing.
Call
jst_checkwithfastafter ordinary work. Usefixfor mechanical repairs andreleaseonce at delivery; do not repeat a passing gate or run its internal scripts separately.
Install: Pi
npm install --save-dev @jst-stack/mcpLoad the extension (the four tools are registered automatically):
pi -e ./node_modules/@jst-stack/mcp/dist/pi/extension.jsOr reference the package subpath @jst-stack/mcp/pi from your Pi extensions configuration. The tools appear as jst_start_task, jst_scaffold_slice, jst_get_recipe, and jst_check; projectRoot defaults to the session working directory.
Architecture
Dependency direction:
domain(contracts) →application(services) →infrastructure(adapters) →composition(MCP/Pi).The MCP transport contains no project/business policy.
External effects (process spawn, filesystem) sit behind narrow ports and are replaceable in tests.
Architecture sections and recipes are parsed from the project-local skill by a pure Markdown section parser; no AI summarization and no embedded architecture prose.
Commands run via argument arrays; user values are never interpolated into a shell string.
All tool inputs and project paths are validated fail-fast.
Development
npm install
npm run check # lint + build + test + npm pack --dry-runKnown limitations
jst_scaffold_sliceruns the generator twice: a--dry-runto read the exact file plan, then the real run (which installs dependencies unless--no-installis passed).Diagnostic summaries are bounded to the last 4000 characters; full output is not preserved.
jst_start_taskandjst_get_reciperequireskills/frontend-architecture/SKILL.mdin the project root. Each returned section is bounded to 4000 characters and the selected section set to 6500 characters.
This server cannot be deployed
Maintenance
Related MCP Connectors
Access and maintain design system docs, tokens, components, skills, and contexts across any project.
Build, run and publish Workbench flows, tasks, shims and knowledge bases.
Dispatch and track Alchemist Cloud tickets, watch deploys, read logs, and query your project DB.
SketchXFlow delivery team: pull client requirements, post updates, log time, move milestones.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables scaffolding and managing Clean Architecture in Next.js projects, providing tools to initialize structure, create features with all layers, and validate architecture compliance.-
- AlicenseNot gradedqualityDmaintenanceEnables local-first task contract generation and drift/sludge guard checks for coding tasks, with CLI and VS Code extension support.59 npmMIT
- AlicenseNot gradedqualityCmaintenanceBootstraps dev environments by installing, wiring, and verifying CLI tools and MCP servers from curated recipes, and provides scope-aware audit of MCP configurations.MIT
- AlicenseNot gradedqualityCmaintenanceEnables autonomous software engineering workflows by routing intent to specialized modes, managing Fable5 task ledgers and backend contracts, auditing React/TypeScript stacks, generating architectural SVG diagrams, and enforcing write-guard path policies.MIT