Build a one-call budgeted memento session context packet with briefing, prompt recall, vault health, queue status, and expandable note paths. Host-adapter primitive for startup/context injection; use memento_search and memento_get for explicit user recall questions.
AI agents call memento_session_context to retrieve information from Memento Vault without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool assembles a context packet by reading and aggregating existing vault data (briefing, prompts, health status, queue status, note paths). It performs no writes, executions, or deletions. The description explicitly contrasts it with memento_search and memento_get for 'explicit user recall questions,' indicating it is a read-oriented startup utility.
From the tool's definition 'Build a one-call budgeted memento session context packet with briefing, prompt recall, vault health, queue status, and expandable note paths' — aggregates and retrieves existing data; 'Host-adapter primitive for startup/context injection' confirms read-only…
Documented attack patterns abuse exactly the kind of access memento_session_context gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memento Vault, and nothing reaches the server without passing your rules. This is the rule we recommend for memento_session_context:
{
"version": "1",
"default": "deny",
"tools": {
"memento_session_context": {}
}
}memento_session_context is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Build a one-call budgeted memento session context packet with briefing, prompt recall, vault health, queue status, and expandable note paths. Host-adapter primitive for startup/context injection; use memento_search and memento_get for explicit user recall questions. It is categorised as a Read tool in the Memento Vault MCP Server, which means it retrieves data without modifying state.
Register the Memento Vault MCP server in PolicyLayer and add a rule for memento_session_context: 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 Memento Vault. Nothing to install.
memento_session_context 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 memento_session_context 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 memento_session_context. 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.
memento_session_context is provided by the Memento Vault MCP server (sandsower/memento-vault). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memento Vault, 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.
14 Memento Vault tools catalogued and risk-classified — across an index of 43,000+ MCP servers.