AI agents call project_brief 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 retrieves and queries project information from persistent markdown files without any side effects. It assembles and presents existing data but does not create, modify, delete, or execute anything. The blast radius of misuse is minimal—an agent could access project details it shouldn't see, but cannot alter or destroy data or trigger external operations. This is a classic Read category tool.
From the tool's definition Tool description states it "Load[s] full context for a single project" including "description, body, open tasks, blocked tasks, knowledge files, and recent session logs." The verb "load" and the passive retrieval of existing project data indicates a read-only…
Attacks that exploit this kind of access
Load full context for a single project: description, body, open tasks, blocked tasks, knowledge files, and recent session logs. Use this when you need to dive deep into one project. 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_brief: 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_brief 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_brief 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_brief. 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_brief 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 →