List recently viewed Backlog projects
AI agents call list_recent_projects to retrieve information from Backlog MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a list of recently viewed projects. It is a passive read operation that retrieves data without creating, modifying, deleting, executing code, or committing financial actions. The blast radius of misuse is minimal—an attacker could only discover which projects a user has recently accessed, which is low-sensitivity metadata in most contexts.
From the tool's definition Tool name 'list_recent_projects' and description 'List recently viewed Backlog projects' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List recently viewed Backlog projects. It is categorised as a Read tool in the Backlog MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Backlog MCP Server MCP server in PolicyLayer and add a rule for list_recent_projects: 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 Backlog MCP Server. Nothing to install.
list_recent_projects 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 list_recent_projects 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 list_recent_projects. 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.
list_recent_projects is provided by the Backlog MCP Server MCP server (katsuhirohonda/mcp-backlog-server). 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 →