AI agents call context_assemble to retrieve information from Cortex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the naming pattern and server context, 'context_assemble' most likely retrieves and assembles relevant memory/context data from the Cortex memory system. No write, execute, destructive, or financial operations are implied. The empty description prevents higher confidence, but the consistent pattern across sibling tools (all retrieval-oriented) supports a Read classification.
From the tool's definition Tool name 'context_assemble' and sibling tools (memory_get, memory_recall, memory_list, memory_graph, active_memory_slice) all suggest retrieval and querying of persistent memory data stored in an Obsidian vault.
Documented attack patterns abuse exactly the kind of access context_assemble gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cortex, and nothing reaches the server without passing your rules. This is the rule we recommend for context_assemble:
{
"version": "1",
"default": "deny",
"tools": {
"context_assemble": {}
}
}context_assemble 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.
context_assemble. It is categorised as a Read tool in the Cortex MCP Server, which means it retrieves data without modifying state.
Register the Cortex MCP server in PolicyLayer and add a rule for context_assemble: 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 Cortex. Nothing to install.
context_assemble 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 context_assemble 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 context_assemble. 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.
context_assemble is provided by the Cortex MCP server (tt-wang/memem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 Cortex tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 Cortex tools catalogued and risk-classified — across an index of 42,500+ MCP servers.