Start a session. Loads rules, last summary, sprint goals, recent decisions.
AI agents call memory_session_start to retrieve information from Claude Memory MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool reads and loads existing data (rules, summaries, goals, decisions) into the session context. There are no side effects described — it retrieves stored information without creating, modifying, or deleting anything. Severity is low because misuse only exposes stored project memory data.
From the tool's definition Loads rules, last summary, sprint goals, recent decisions
Attacks that exploit this kind of access
Start a session. Loads rules, last summary, sprint goals, recent decisions. It is categorised as a Read tool in the Claude Memory MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Memory MCP server in PolicyLayer and add a rule for memory_session_start: 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 Memory MCP. Nothing to install.
memory_session_start 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 memory_session_start 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 memory_session_start. 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.
memory_session_start is provided by the Claude Memory MCP server (navid-kianfar/claude-memory-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 →