Boot AI agent context. Two modes:\n1. Default: returns skeleton + docs (2-3k tokens) for structure overview.\n2. includeFiles: [
AI agents call get_ai_context to retrieve information from Project Graph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns contextual information (skeleton structure and documentation) to initialize AI agent context. It performs a read-only operation with no side effects, data modification, code execution, or destructive capabilities. The two modes both involve returning pre-existing information in different scopes. Classified as Read due to pure information retrieval nature.
From the tool's definition Tool name 'get_ai_context' and description 'returns skeleton + docs' indicate retrieval of documentation and code structure information without modification or execution capabilities.
Attacks that exploit this kind of access
Boot AI agent context. Two modes:\n1. Default: returns skeleton + docs (2-3k tokens) for structure overview.\n2. includeFiles: [. It is categorised as a Read tool in the Project Graph MCP Server, which means it retrieves data without modifying state.
Register the Project Graph MCP server in PolicyLayer and add a rule for get_ai_context: 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 Project Graph. Nothing to install.
get_ai_context 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_ai_context 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_ai_context. 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_ai_context is provided by the Project Graph MCP server (rnd-pro/project-graph-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 →