
MCP Spec Generator
Generates project specifications and file structures using Claude AI through MCP integration. Enables users to describe project ideas and automatically create corresponding documentation and project files.
README
MCP Spec Generator (docs)
Minimal notes for running and developing the MCP spec-generator tool described in this repo.
Requirements
- Node.js LTS (>=18)
- Environment variable:
ANTHROPIC_API_KEY
(store securely)
Quick notes
- The server communicates with Anthropic's
claude-4-sonnet-20240620
model. Keep temperature at0.0
for deterministic output. - Do not run with write permissions in production: MCP tools should return
create_file
/edit_file
calls for user approval in Cursor. - Example
.cursor/mcp.json
is provided in the repo as a template. When configuring, whitelist only the project folder.
Testing
- There are fixtures in
tests/fixtures/
to validate the expected Markdown outputs from the model.
How to run
- Run tests:
node tests/run_tests.js
ornpm test
. - Dry-run (propose files):
node index.js "My project idea..."
- Persist files:
node index.js "My project idea..." --allow-write
- Read prompt from stdin:
echo "My idea" | node index.js
Linting & formatting
- ESLint and Prettier configs are included. To lint/format locally run:
npm run lint
npm run format
Environment & setup (required)
- Set your Anthropic API key in the environment before running the tool:
- Linux/macOS:
export ANTHROPIC_API_KEY=sk-...
- Windows (PowerShell):
setx ANTHROPIC_API_KEY "sk-..."
- Linux/macOS:
- Optionally copy
env.example
to.env
or export additional overrides likeMCP_AUDIT_FILE
orANTHROPIC_TIMEOUT_MS
. - Make the CLI executable if you prefer:
chmod +x index.js
Cursor MCP configuration
- The repo includes
.cursor/mcp.json
configured to whitelist the project path. Verify it points to your repository root before registering with Cursor.
Security
- Never point the Filesystem MCP server at
~
or your home directory. Whitelist only the necessary project paths.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.