// MCP TOOL REFERENCE

AI AGENT SCRATCHPAD TOOLS

6 tools from the Ai Agent Scratchpad MCP Server, categorised by risk level.

View the Ai Agent Scratchpad policy → Token cost: 638 tokens →

// ALL 6 AI AGENT SCRATCHPAD TOOLS

READ 4 tools

Read scratchpad_checkpoint 현재 세션 상태의 스냅샷을 체크포인트 태그로 저장합니다. keys를 지정하면 해당 키만 스냅샷. Read scratchpad_diff 현재 키 값과 체크포인트 값의 diff를 반환합니다. 또는 두 임의 값의 diff 비교. Read scratchpad_list 세션의 모든 키 목록을 반환합니다. 선택적 prefix 필터링 지원. Read scratchpad_read 세션의 특정 키 값을 조회합니다.

WRITE 1 tools

Write scratchpad_write 세션에 키-값을 저장합니다. value는 문자열 또는 JSON 직렬화 가능한 값.

DESTRUCTIVE 1 tools

Destructive scratchpad_delete 세션의 특정 키를 삭제합니다.

// FAQ

How many tools does the Ai Agent Scratchpad MCP server have? +

The Ai Agent Scratchpad MCP server exposes 6 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Ai Agent Scratchpad tools? +

Route the Ai Agent Scratchpad 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 Ai Agent Scratchpad tools fall into? +

Ai Agent Scratchpad tools are categorised as Read (4), Write (1), Destructive (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.