AI agents call session_replay 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 queries existing session event data in chronological order, which is a read-only operation with no side effects. It does not create, modify, delete, execute code, or commit financial transactions. The blast radius of misuse is minimal—an agent could only access historical information it may already have access to.
From the tool's definition Tool name 'session_replay' and description 'Get the full timeline of events for a session, in chronological order' indicate retrieval of historical session data with no modification or execution capability.
Attacks that exploit this kind of access
Get the full timeline of events for a session, in chronological order. 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 session_replay: 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.
session_replay 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 session_replay 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 session_replay. 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.
session_replay 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 →