AI agents call get_decisions 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 retrieves existing architectural decision records (ADRs) from a shared project context store. The use of 'Retrieve' and the optional filtering by status confirm this is a read-only operation that queries data without creating, modifying, deleting, or executing anything. No destructive, financial, or executable operations are involved.
From the tool's definition Tool name 'get_decisions' combined with description 'Retrieve architectural decisions (ADRs) for a project' indicates a query/retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Retrieve architectural decisions (ADRs) for a project, optionally filtered by status. 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_decisions: 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_decisions 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_decisions 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_decisions. 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_decisions 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 →