Re-read the project primer from
AI agents call get_project_primer to retrieve information from Domain memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing project documentation/primer information without modifying, deleting, or executing anything. It has no side effects and serves to query stored knowledge about the project. The blast radius of misuse is minimal — an agent might retrieve stale or incomplete information but cannot corrupt, delete, or execute operations.
From the tool's definition Tool name is 'get_project_primer' and description indicates it 're-reads' or retrieves project primer content. The verb 'read' and the retrieval nature align with the Read category.
Attacks that exploit this kind of access
Re-read the project primer from. It is categorised as a Read tool in the Domain memory MCP Server, which means it retrieves data without modifying state.
Register the Domain memory MCP server in PolicyLayer and add a rule for get_project_primer: 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 Domain memory. Nothing to install.
get_project_primer 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_primer 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_primer. 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_primer is provided by the Domain memory MCP server (mashware/domain-memory). 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 →