New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

dephq_project_init

Scaffold a complete Dephq React and TypeScript project. Choose a page, records app, API-backed tool, or full app with frontend and server capabilities. Creation is transactional and existing files are never overwritten.

SERVERDephq SOURCE@dephq/mcp
Medium RISK CLASS
Category Write
Parameters 92 required
Recommended Rate-limitedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/dephq-mcp/dephq-project-init.md

What dephq_project_init does on Dephq

AI agents use dephq_project_init to create or update resources in Dephq, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dephq environment.

ParameterTypeRequiredDescription
name string Yes
slug string
access string
framework string
description string
capabilities array
project_path string Yes
project_type string
install_dependencies boolean

Parameters from the server's own tool schema.

Why dephq_project_init is rated Medium

This tool creates new project files and scaffolding. It explicitly states existing files are never overwritten, making it a reversible write operation (new file creation) rather than destructive. The severity is medium since it creates potentially many files on the filesystem, but misuse has limited blast radius given the no-overwrite guarantee.

From the tool's definition Scaffold a complete Dephq React and TypeScript project... Creation is transactional and existing files are never overwritten.

Questions about dephq_project_init

What does the dephq_project_init tool do? +

Scaffold a complete Dephq React and TypeScript project. Choose a page, records app, API-backed tool, or full app with frontend and server capabilities. Creation is transactional and existing files are never overwritten. It is categorised as a Write tool in the Dephq MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does dephq_project_init accept? +

dephq_project_init accepts 9 parameters: name, slug, access, framework, description, capabilities, project_path, project_type, install_dependencies. Required: name, project_path. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on dephq_project_init? +

Register the Dephq MCP server in PolicyLayer and add a rule for dephq_project_init: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Dephq. Nothing to install.

What risk level is dephq_project_init? +

dephq_project_init is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit dephq_project_init? +

Yes. Add a rate_limit block to the dephq_project_init rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block dephq_project_init completely? +

Set action: deny in the PolicyLayer policy for dephq_project_init. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides dephq_project_init? +

dephq_project_init is provided by the Dephq MCP server (@dephq/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Dephq, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Dephq's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.