Summarize a previously-fetched handoff bundle: README contents, entry HTML, file type counts, and a preview of the entry file.
AI agents call inspect_bundle 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.
This tool retrieves and displays information about an already-fetched bundle (README, HTML, file counts, previews) without creating, modifying, deleting, or executing external operations. It is purely a Read operation with minimal risk—suitable for inspection and analysis only.
From the tool's definition Tool description states 'Summarize a previously-fetched handoff bundle' and lists read-only operations: 'README contents, entry HTML, file type counts, and a preview'. The verb 'Summarize' and 'preview' indicate data retrieval with no modifications.
Attacks that exploit this kind of access
Summarize a previously-fetched handoff bundle: README contents, entry HTML, file type counts, and a preview of the entry file. 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 inspect_bundle: 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.
inspect_bundle 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 inspect_bundle 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 inspect_bundle. 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.
inspect_bundle 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 →