# create_project

Create a new Stitch project

Agent View of the PolicyLayer registry record for `create_project`. HTML page: https://policylayer.com/tools/0x-professor-stitch-mcp-server/create-project

## Facts

- Tool: `create_project`
- Server: Stitch MCP Server (`0x-professor/stitch-mcp-server`) — https://policylayer.com/tools/0x-professor-stitch-mcp-server.md
- Homepage: https://github.com/0x-Professor/Stitch-mcp-server
- Risk category: Write (Medium risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "create_project",
    "arguments": {}
  }
}
```

## Why create_project is rated Medium

Creating a new project is a write operation that modifies the state of the system by adding a new resource. It is reversible (the project can be deleted), so it does not qualify as Destructive. There are no code execution, data deletion, or financial implications.

From the tool's own definition: "Tool name 'create_project' and description 'Create a new Stitch project' indicate creation of a new project resource. This is a reversible write operation (projects can be deleted or modified)."

## Use case

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

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Stitch MCP Server:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_project": {
      "limits": [
        {
          "counter": "create_project_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Stitch MCP Server (8)

- `get_screen_code` — Read — https://policylayer.com/tools/0x-professor-stitch-mcp-server/get-screen-code.md
- `get_screen_image` — Read — https://policylayer.com/tools/0x-professor-stitch-mcp-server/get-screen-image.md
- `list_projects` — Read — https://policylayer.com/tools/0x-professor-stitch-mcp-server/list-projects.md
- `edit_screen` — Write — https://policylayer.com/tools/0x-professor-stitch-mcp-server/edit-screen.md
- `generate_and_fetch_code` — Write — https://policylayer.com/tools/0x-professor-stitch-mcp-server/generate-and-fetch-code.md
- `generate_screen` — Write — https://policylayer.com/tools/0x-professor-stitch-mcp-server/generate-screen.md
- `generate_variants` — Write — https://policylayer.com/tools/0x-professor-stitch-mcp-server/generate-variants.md
- `scaffold_project_files` — Write — https://policylayer.com/tools/0x-professor-stitch-mcp-server/scaffold-project-files.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=0x-professor-stitch-mcp-server · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/0x-professor-stitch-mcp-server