AI agents call get_project_summary to retrieve information from Handoff without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves existing project metadata without side effects. It is a read-only operation that aggregates stored context information for display purposes. The blast radius of misuse is minimal—an agent could potentially access sensitive project details, but cannot modify, delete, or execute code. Low severity appropriate for informational retrieval in a shared memory system.
From the tool's definition Tool name contains 'get' and description states it retrieves a 'complete overview' of project data (architecture, stack, patterns, decisions, sessions). No modification, deletion, or execution verbs present.
Attacks that exploit this kind of access
Get a complete overview of the project: architecture, stack, patterns, decisions, and recent sessions. It is categorised as a Read tool in the Handoff MCP Server, which means it retrieves data without modifying state.
Register the Handoff MCP server in PolicyLayer and add a rule for get_project_summary: 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 Handoff. Nothing to install.
get_project_summary 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 get_project_summary 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 get_project_summary. 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.
get_project_summary is provided by the Handoff MCP server (juan-severiano/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 →