Provides sandboxed Git repository management for NSTOK repositories, including status inspection, diffs, feature branch creation, conventional commits, and pull requests for human review.
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., "@NSTOK AI Software Factory MCP Server Analyze this PRD and create an app plan reusing existing features."
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.
An enterprise-grade Model Context Protocol (MCP) server implemented in TypeScript that powers the NSTOK AI Software Factory. It allows reasoning agents (such as Codex, Antigravity, or Claude) to construct production-ready NSTOK applications directly from PRDs by discovering and reusing existing ecosystem capabilities, UI components, database models, and templates.
SEARCH ā REUSE ā ADAPT ā CREATEThe system strictly enforces the principle: Never generate code from scratch if an existing asset can satisfy or be adapted to the requirement.
Reuse First: Prioritize existing business features (Nstok-feature-*), UI components (Nstok-ui), and database models (Nstok-db).
Template First: Applications start from Nstok-app-template; features start from Nstok-feature-template.
Knowledge Before Code: Understand architecture, dependencies, and patterns before mutating code.
Plan Before Mutation: Analyze ā Plan ā Approve ā Implement ā Validate.
Closed Knowledge Loop: Every newly generated application or feature enriches the central Knowledge Graph (Nstok-knowledge-master).
Related MCP server: Vibe Coder MCP Server
āāāāāāāāāāāāāāāāāāāāāāāāā
ā CODEX ā
ā User / PRD / Task ā
āāāāāāāāāāāāā¬āāāāāāāāāāāā
ā MCP (Stdio / SSE)
ā¼
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā NSTOK MCP SERVER ā
ā ā
ā ā¢ PRD Analysis ā
ā ā¢ Knowledge Graph & Vector ā
ā ā¢ Feature & UI Discovery ā
ā ā¢ Template Orchestrator ā
ā ā¢ Architecture Validator ā
ā ā¢ Sandboxed Git Management ā
āāāāāāāāāāāāāāāāāā¬āāāāāāāāāāāāāāāāā
ā
āāāāāāāāāāāāāāāāāāāāāāāā¼āāāāāāāāāāāāāāāāāāāāāāā
ā ā ā
ā¼ ā¼ ā¼
āāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāā
ā Knowledge ā ā Repositories ā ā Job Runner ā
ā Master ā ā Ecosystem ā ā (Worker) ā
ā ā ā ā ā ā
ā Graph + RAG ā ā UI, DB, Apps ā ā Test / Lint ā
ā & Metadata ā ā & Features ā ā Typecheck ā
āāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāānstok-mcp/
āāā src/
ā āāā index.ts # CLI entrypoint (Stdio transport)
ā āāā server.ts # MCP server instance & tool registration
ā ā
ā āāā config/
ā ā āāā environment.ts # Environment variables, security allowlists, timeouts
ā ā
ā āāā domain/ # Core domain models & graph types
ā ā āāā app.ts # Application entity
ā ā āāā feature.ts # Feature & capability interfaces
ā ā āāā component.ts # UI component definitions
ā ā āāā database.ts # DB entities & relations
ā ā āāā repository.ts # Repository metadata & graph relationships
ā ā āāā plan.ts # Structured AppPlan & FeaturePlan schemas
ā ā āāā graph.ts # Graph nodes, edges & traversal results
ā ā
ā āāā services/ # Business logic layers
ā ā āāā knowledge.service.ts # Hybrid search & graph traversal engine
ā ā āāā repository.service.ts # Sandboxed workspace operations & template cloning
ā ā āāā generation.service.ts # PRD analysis & Reuse Decision Engine
ā ā āāā git.service.ts # Git branching, commit, diff & PR workflow
ā ā āāā validation.service.ts # Architecture validator (UI-001, DB-001) & jobs
ā ā āāā audit.service.ts # Audit logging for tracking operations
ā ā
ā āāā tools/ # MCP Tool definitions
ā ā āāā knowledge/ # search_knowledge, find_features, find_ui_components, etc.
ā ā āāā generation/ # analyze_prd, create_app_plan, create_app, etc.
ā ā āāā repository/ # read_file, write_file, search_repo_code, git ops
ā ā āāā validation/ # validate_architecture, run_tests, update_knowledge
ā ā
ā āāā data/
ā āāā seed.ts # Pre-seeded NSTOK ecosystem metadata & graph
ā
āāā tests/
ā āāā knowledge.test.ts # Discovery & graph traversal tests
ā āāā generation.test.ts # PRD analysis & planning tests
ā āāā validation.test.ts # Architecture validation tests
ā āāā server.test.ts # Server instantiation & tool registration tests
ā
āāā package.json
āāā tsconfig.json
āāā README.mdTool | Description |
| Hybrid keyword and semantic search across knowledge assets, features, UI, and DB entities. |
| Discover reusable business features ( |
| Find reusable design system components in |
| Search database schemas and entity definitions in |
| Search established architectural patterns, code conventions, and guidelines in NSTOK. |
| Retrieve full repository metadata, contained assets, and graph edges for any NSTOK repo. |
| Deep-dive feature context (routes, UI/DB dependencies, and graph traversal). |
| Retrieve full composition details and graph relations for an application. |
Tool | Description |
| Analyze raw PRD text, extract required capabilities, match reusable vs missing assets, and calculate reuse score. |
| Generate a structured application implementation plan following |
| Generate a structured feature development plan scaffolded from |
Tool | Description |
| Clone |
| Clone |
| Link and integrate an existing or new feature module into an application. |
| End-to-end scaffolding orchestrator: clones template, wires reused features, creates missing features, and outputs app composition. |
| Scaffold a new feature module from template when missing capabilities are required. |
Tool | Description |
| Safely read file content within an NSTOK repository with audit logging. |
| Safely write or update a file within an NSTOK repository with audit logging. |
| Search for code snippets and symbols within an NSTOK repository. |
| Get git status, active branch, and modified files for a repository. |
| Inspect git diff before committing changes. |
| Create a feature branch ( |
| Create a structured commit with conventional commit message. |
| Propose a Pull Request to |
Tool | Description |
| Enforce architecture rules: |
| Run unit and integration test suites in an isolated environment. |
| Run linting and static analysis on a repository. |
| Run project build and TypeScript compilation. |
| Feed newly generated application or feature metadata back into |
Node.js >= 18 (Tested on Node.js 24)
npm >= 9
git clone <repository_url> nstok-mcp
cd nstok-mcp
npm installnpm run buildnpm testnpm run devAdd the following snippet to your mcp_config.json or claude_desktop_config.json:
{
"mcpServers": {
"nstok-software-factory": {
"command": "node",
"args": ["<PATH_TO_NSTOK_MCP>/dist/index.js"],
"env": {
"NODE_ENV": "production",
"ENABLE_AUDIT_LOG": "true"
}
}
}
}When a developer requests:
"Codex, please build
nstok-app-wbased on this PRD: POS with authentication, product catalog, inventory, checkout, and daily sales report."
The MCP server coordinates the following pipeline:
1. analyze_prd("Nstok-app-w", PRD)
āāā Extracted: auth, product, inventory, checkout, payment, sales-report
āāā Reused: Nstok-feature-a, Nstok-feature-b, Nstok-feature-c, checkout-payment
āāā Missing: sales-report (Scaffold Nstok-feature-sales-report)
āāā Reuse Score: 80%
2. create_app_plan("Nstok-app-w", PRD)
āāā Generates structured implementation plan
3. create_branch("Nstok-app-w", "feature/ai/create-nstok-app-w")
4. create_app("Nstok-app-w", PRD)
āāā Clones Nstok-app-template
āāā Links reused features
āāā Scaffolds Nstok-feature-sales-report from Nstok-feature-template
5. validate_architecture("Nstok-app-w")
āāā Checks UI-001 (all UI from Nstok-ui) and DB-001 (all schema from Nstok-db)
6. run_tests("Nstok-app-w") & run_build("Nstok-app-w")
7. create_commit("Nstok-app-w", "feat: initial scaffolding for nstok-app-w")
8. create_pull_request("Nstok-app-w", "feat: nstok-app-w implementation", summary)
9. update_knowledge(...)
āāā Central graph updated so future apps can reuse Nstok-feature-sales-report!Repository Allowlist: Enforces Nstok-* repository naming pattern.
Path Traversal Protection: All filesystem reads and writes are sandboxed to the active workspace.
Audit Trail: Every mutation (write_file, create_branch, create_commit, create_pull_request) is appended to audit.log.jsonl.
Command Allowlist: Strict restrictions on executable commands (node, npm, npx, git, tsc).
MIT Ā© NSTOK Engineering
Integrate and link an existing or newly created feature into an application workspace.
Inputs: appName (required), featureRepository (required).
Analyze a PRD text, extract required capabilities, match reusable vs missing assets, and compute reuse score.
Inputs: prd (required), appName (required).
Clone the standard baseline Nstok-app-template to initialize a new application workspace.
Inputs: appName (required), templateName.
Clone the standard Nstok-feature-template to initialize a new feature repository.
Inputs: description (required), featureName (required), templateName.
Orchestrate end-to-end application generation from PRD, prioritizing feature reuse and template baselines.
Inputs: prd (required), name (required), template.
Generate a structured application implementation plan following the SEARCH -> REUSE -> ADAPT -> CREATE principle.
Inputs: prd (required), appName (required), template.
Create a new feature branch (e.g. feature/ai/create-nstok-app-w) following NSTOK git workflow.
Inputs: branchName (required), repository (required).
Create a structured git commit with a conventional commit message.
Inputs: message (required), repository (required), files.
Scaffold a new feature module from Nstok-feature-template when missing capabilities are required.
Inputs: featureName (required), capabilities (required), description.
Generate a structured feature development plan scaffolded from Nstok-feature-template.
Inputs: featureName (required), capabilities (required).
Propose a Pull Request to main branch for human review and approval.
Inputs: body (required), title (required), repository (required), targetBranch.
Search database schemas and entity definitions in Nstok-db (Product, Inventory, Sale, User, etc.).
Inputs: query.
Search established architectural patterns, code conventions, and guidelines in NSTOK.
Inputs: query, category.
Discover reusable business features from the NSTOK ecosystem (e.g. Nstok-feature-a, b, c) matching capabilities or keywords.
Inputs: query, capabilities.
Find reusable design system UI components in Nstok-ui (DataTable, ProductTable, SearchInput, Button, etc.).
Inputs: query, category.
Get full application architecture and composition details for a generated or production app.
Inputs: appName (required).
Get deep-dive context for a specific feature, including capabilities, routes, UI/DB deps, and graph traversal.
Inputs: featureId (required).
Get full repository context, contained assets, and graph relationships for any NSTOK repo.
Inputs: repositoryName (required).
Inspect git diff in a repository before committing mutations.
Inputs: repository (required), staged.
Get git status, active branch, and modified files for a repository.
Inputs: repository (required).
Safely read a file inside an NSTOK repository with audit logging and sandbox isolation.
Inputs: path (required), repository (required).
Run build and TypeScript type-checking for an application or feature.
Inputs: repository (required).
Run linting and static analysis on an NSTOK repository.
Inputs: repository (required).
Run unit and integration test suites in an isolated environment.
Inputs: repository (required), testFilter.
Search across all NSTOK knowledge assets, features, UI components, DB entities, patterns, and repositories using hybrid search.
Inputs: query (required), type, repository.
Search for code snippets, symbol definitions, and text within an NSTOK repository.
Inputs: query (required), repository (required), extensions.
Feed newly generated application or feature metadata back into Nstok-knowledge-master.
Inputs: id (required), name (required), type (required), repository (required), +6 more.
Validate that code obeys NSTOK architectural rules (UI-001, DB-001, ARCH-001, DEP-001).
Inputs: repository (required).
Safely write or update a file inside an NSTOK repository with audit logging.
Inputs: path (required), content (required), repository (required), overwrite.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
Scored across 29 tools
Several tools have overlapping purposes: search_knowledge, find_features, find_ui_components, find_db_entities, find_existing_patterns, and search_repo_code all perform search-like operations. Similarly, create_app_plan and create_feature_plan both generate plans. However, descriptions provide some distinction through specific resource types and workflows.
Most tools follow a verb_noun pattern (e.g., search_knowledge, find_features, create_app_plan, clone_app_template). Minor deviations like get_project_context and run_tests are still readable and consistent with the pattern. Overall naming is predictable and consistent.
With 29 tools, the set is heavy and may overwhelm an agent. The high count is somewhat justified by the complex domain of software generation and knowledge management, but several tools appear redundant (e.g., multiple find_ tools, multiple create_plan tools), suggesting over-scoping.
The surface covers search, planning, creation, file operations, git workflow, validation, testing, and knowledge updating, which is comprehensive for a software factory. Minor gaps might include direct code editing tools or more granular git operations (e.g., merge, delete branch), but core workflows appear covered.
Turn PRDs and product ideas into structured specs so coding agents build your intent, not theirs.
Git-backed platform for skills, tools, and context for AI agents
Register, deploy, review, and govern internal applications built with coding agents.
Intelligent product canvas: iterate on your product's design with your coding agent, synced to code.
