AI agents call get_project_memory to retrieve information from RoadBoard 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 memory entries associated with a project. The verb 'list' and the absence of any language suggesting creation, modification, or deletion confirms this is a Read operation. Severity is low because listing memory entries poses minimal risk—it only exposes information already stored in the project context, with no destructive or operational consequences.
From the tool's definition Tool name 'get_project_memory' and description 'List memory entries for a project' indicate a read-only retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List memory entries for a project. It is categorised as a Read tool in the RoadBoard MCP Server, which means it retrieves data without modifying state.
Register the RoadBoard MCP server in PolicyLayer and add a rule for get_project_memory: 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 RoadBoard. Nothing to install.
get_project_memory 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_memory 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_memory. 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_memory is provided by the RoadBoard MCP server (maless88/roadboard). 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 →