Reads AI_CONTEXT.md from the current project and returns its contents (checks root, docs/ and doc/)
AI agents call get_project_context to retrieve information from Ginialtech without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and returns file contents without side effects. It queries project context documentation to inform AI agents of conventions and requirements. The blast radius of misuse is minimal—the worst outcome is that an agent gains access to project context information, which is intended to be visible within the project scope.
From the tool's definition Tool performs a read-only operation: 'Reads AI_CONTEXT.md from the current project and returns its contents'. No modification, deletion, execution, or financial operation is described.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Reads AI_CONTEXT.md from the current project and returns its contents (checks root, docs/ and doc/). It is categorised as a Read tool in the Ginialtech MCP Server, which means it retrieves data without modifying state.
Register the Ginialtech MCP server in PolicyLayer and add a rule for get_project_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 Ginialtech. Nothing to install.
get_project_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_project_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_project_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_project_context is provided by the Ginialtech MCP server (marcelaborgarello/ginialteach-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 →