AI agents call ledger_stats to retrieve information from Engram 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 statistics (counts grouped by various dimensions) from a ledger without creating, modifying, deleting, or executing any operations. It is a read-only query operation with minimal blast radius if misused by an agent—the worst outcome would be disclosure of statistics the agent shouldn't access, not data corruption or external effects.
From the tool's definition Tool name 'ledger_stats' and description 'Get ledger statistics: counts by status, plane, and tensions' indicate retrieval of aggregated statistical data with no modification or side effects.
Attacks that exploit this kind of access
Get ledger statistics: counts by status, plane, and tensions. It is categorised as a Read tool in the Engram MCP Server, which means it retrieves data without modifying state.
Register the Engram MCP server in PolicyLayer and add a rule for ledger_stats: 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 Engram. Nothing to install.
ledger_stats 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 ledger_stats 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 ledger_stats. 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.
ledger_stats is provided by the Engram MCP server (tinydarkforge/engram). 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 →