AI agents call project_list to retrieve information from Recap 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 project metadata from the workspace without creating, modifying, deleting, or executing any operations. It is a straightforward read operation with filtering capabilities. The blast radius of misuse is minimal—an agent could only obtain information about existing projects, not alter system state.
From the tool's definition Tool description states 'List projects in the workspace' and 'Returns slug, name, description, task counts, and last-touched dates.' The verb 'list' and 'returns' indicate data retrieval with no modification or side effects.
Attacks that exploit this kind of access
List projects in the workspace. Filter by status (active, archived, all). Returns slug, name, description, task counts, and last-touched dates. It is categorised as a Read tool in the Recap MCP Server, which means it retrieves data without modifying state.
Register the Recap MCP server in PolicyLayer and add a rule for project_list: 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 Recap. Nothing to install.
project_list 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 project_list 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 project_list. 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.
project_list is provided by the Recap MCP server (shivam-singh-git/recap-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 →