Get assembled context
get_contextAssemble relevant memories into context before a task using hybrid retrieval with token budgeting and optional memory-graph expansion, so the AI can adapt to the user's preferences and history.
Instructions
Assemble relevant memories for the current task via hybrid retrieval (+ optional memory-graph expansion), with token budgeting. Use to load memory into context before a task.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "get_context"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of seed memories (default 10) | |
| query | No | Optional focus query to seed hybrid retrieval | |
| userId | No | Scope context to a user (USER scope) | |
| maxTokens | No | Token budget for assembled context (default 2000) | |
| projectId | No | Scope context to a project | |
| sessionId | No | ||
| includeGraph | No | Expand seeds with memory-graph neighbors | |
| includeHistory | No | Include superseded/archived memories |