// MCP TOOL REFERENCE

AVA TOOLS

10 tools from the Ava MCP Server, categorised by risk level.

// ALL 10 AVA TOOLS

READ 2 tools

Read listTasks ユーザーのタスク一覧を取得する。 Read create-react-ui Returns a React-based UI

WRITE 7 tools

Write startTask 開始サマリをSlackに共有するための入力仕様。 Write completeTask 完了報告を共有するための入力仕様。 Write pauseTask タスクを一時休止するための入力仕様。 Write reportBlocked ブロッキング情報を共有するための入力仕様。 Write resolveBlocked ブロッキングが解決したことを報告する入力仕様。 Write resumeTask 一時休止したタスクを再開するための入力仕様。 Write updateTask 進捗の抽象的サマリを共有するための入力仕様。

DESTRUCTIVE 1 tools

Destructive cancelTask タスク中止を受け付けるための入力仕様。

// FAQ

How many tools does the Ava MCP server have? +

The Ava MCP server exposes 10 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Ava tools? +

Route the Ava server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Ava tools fall into? +

Ava tools are categorised as Read (2), Write (7), Destructive (1). Each category has a recommended default policy.

Enforce policy on every Ava tool call.

Start from Ava, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.