Read the full README.md from a fetched handoff bundle. Claude Design handoffs always include a README describing the design intent.
AI agents call read_readme to retrieve information from Claude Handoff without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and reads documentation (README.md file) from an already-fetched design bundle. There are no modifications, executions, deletions, or financial implications. This is purely an informational read operation with minimal blast radius if misused—at worst, an agent would display design documentation.
From the tool's definition Tool name is 'read_readme' and description states it 'Read[s] the full README.md from a fetched handoff bundle'. This is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Read the full README.md from a fetched handoff bundle. Claude Design handoffs always include a README describing the design intent. It is categorised as a Read tool in the Claude Handoff MCP Server, which means it retrieves data without modifying state.
Register the Claude Handoff MCP server in PolicyLayer and add a rule for read_readme: 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 Handoff. Nothing to install.
read_readme 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 read_readme 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 read_readme. 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.
read_readme is provided by the Claude Handoff MCP server (kiwuuu/claude-handoff-mcp). 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 →