AI agents use magnyxa_register_project to create or update resources in Magnyxa — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Magnyxa environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
url | string | — | プロジェクトのURL（任意） |
target | string | Yes | ターゲットユーザー |
features | array | — | 主な機能のリスト |
tech_stack | array | — | 使用している技術スタック |
description | string | Yes | サービスの説明 |
service_name | string | Yes | サービス名 |
Parameters from the server's own tool schema.
This tool creates/registers new project data in Magnyxa, a persistent side effect. It does not delete, execute arbitrary code, or move funds. Classification as Write is appropriate. Severity is medium because unauthorized project registration could pollute a registry or associate an AI agent's outputs with a user's account, but cannot directly destroy data or cause financial harm.
From the tool's definition Tool name 'magnyxa_register_project' and description states it 'registers project information to Magnyxa' (プロジェクト情報をMagnyxaに登録します). The verb '登録' (register/record) indicates creation of new data records.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
プロジェクト情報をMagnyxaに登録します。事前にmagnyxa_set_tokenでトークンを設定する必要があります。Claude Codeがプロジェクトを解析した結果を渡してください。. It is categorised as a Write tool in the Magnyxa MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
magnyxa_register_project accepts 6 parameters: url, target, features, tech_stack, description, service_name. Required: target, description, service_name. The full parameter table on this page comes from the server's own tool schema.
Register the Magnyxa MCP server in PolicyLayer and add a rule for magnyxa_register_project: 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 Magnyxa. Nothing to install.
magnyxa_register_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the magnyxa_register_project 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.
Set action: deny in the PolicyLayer policy for magnyxa_register_project. 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.
magnyxa_register_project is provided by the Magnyxa MCP server (@zelklab/magnyxa-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →