AI agents call project_snapshot to retrieve information from Ensemble without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads from the codebase index (which is pre-populated by 'project_index') and produces a summary artifact. It has no side effects on the codebase, does not execute code or commands, does not modify or delete data, and does not involve financial operations. The operation is purely informational retrieval and transformation.
From the tool's definition Tool name 'project_snapshot' and description 'Generate a compact project baseline summary from the codebase index' indicate retrieval and summarization of existing codebase data.
Attacks that exploit this kind of access
Generate a compact project baseline summary from the codebase index. It is categorised as a Read tool in the Ensemble MCP Server, which means it retrieves data without modifying state.
Register the Ensemble MCP server in PolicyLayer and add a rule for project_snapshot: 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 Ensemble. Nothing to install.
project_snapshot 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_snapshot 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_snapshot. 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_snapshot is provided by the Ensemble MCP server (lynkbyte/ensemble). 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 →