AI agents call get_project_context to retrieve information from Claude without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries project context data (decisions, state, pending items) for reading purposes. No data is created, modified, deleted, or used to trigger external operations. The sibling tools 'recall' and 'remember' on this RAG-based memory server further confirm this is a read operation within a retrieval-augmented generation system.
From the tool's definition Tool description states 'Carga el contexto completo de un proyecto' (loads complete context of a project), listing decisions, status, and pending items.
Attacks that exploit this kind of access
Carga el contexto completo de un proyecto: decisiones, estado, pendientes. It is categorised as a Read tool in the Claude MCP Server, which means it retrieves data without modifying state.
Register the Claude 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 Claude. 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 Claude MCP server (zcc-cddg-mx/mcp-server-claude). 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 →