テーマや問題を構成要素に分解します
AI agents call decompose to retrieve information from Claude MCP Server Integration without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The decompose tool appears to perform analytical breakdown of themes or problems into their components. This is a read-only analytical operation with no side effects—it retrieves/processes information but does not create, modify, delete, or execute external operations. No reversible or irreversible data changes occur. Classified as Read with low severity due to lack of side effects and data modification capabilities.
From the tool's definition Tool name 'decompose' with description 'decompose theme or problem into constituent elements' indicates analysis/decomposition of concepts without data modification.
Attacks that exploit this kind of access
テーマや問題を構成要素に分解します. It is categorised as a Read tool in the Claude MCP Server Integration MCP Server, which means it retrieves data without modifying state.
Register the Claude MCP Server Integration MCP server in PolicyLayer and add a rule for decompose: 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 Claude MCP Server Integration. Nothing to install.
decompose is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the decompose 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 decompose. 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.
decompose is provided by the Claude MCP Server Integration MCP server (mokemoke0821/claude-mcp-integration). 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 →