Generate and save Cursor session summary with learnings
AI agents use cursor_session_summary to create or update resources in SAM — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your SAM environment.
This tool writes data to storage by saving session summaries and extracted learnings. While it does not delete or overwrite existing data irreversibly, and does not execute arbitrary code or move money, it does create and persist new records.
From the tool's definition Tool performs 'Generate and save Cursor session summary' — the 'save' operation creates or modifies persistent data (session summaries and learnings) without deletion.
Documented attack patterns abuse exactly the kind of access cursor_session_summary gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SAM, and nothing reaches the server without passing your rules. This is the rule we recommend for cursor_session_summary:
{
"version": "1",
"default": "deny",
"tools": {
"cursor_session_summary": {
"limits": [
{
"counter": "cursor_session_summary_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}cursor_session_summary stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate and save Cursor session summary with learnings. It is categorised as a Write tool in the SAM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SAM MCP server in PolicyLayer and add a rule for cursor_session_summary: 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 SAM. Nothing to install.
cursor_session_summary is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cursor_session_summary 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 cursor_session_summary. 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.
cursor_session_summary is provided by the SAM MCP server (pigrieco/mcp-memory-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SAM, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
37 SAM tools catalogued and risk-classified — across an index of 43,000+ MCP servers.