localnest_memory_recall
Retrieve relevant local memories for tasks or queries using semantic search and project context to support AI agents with codebase access.
Instructions
Recall the most relevant local memories for a task or query.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| root_path | No | ||
| project_path | No | ||
| branch_name | No | ||
| topic | No | ||
| feature | No | ||
| kind | No | knowledge | |
| limit | No | ||
| response_format | No | json |
Implementation Reference
- src/mcp/tools/memory-workflow.js:86-98 (handler)The handler function for 'localnest_memory_recall' which calls 'memory.recall' and normalizes the result.
async ({ query, root_path, project_path, branch_name, topic, feature, kind, limit }) => normalizeMemoryRecallResult( await memory.recall({ query, rootPath: root_path, projectPath: project_path, branchName: branch_name, topic, feature, kind, limit }), query ) - src/mcp/tools/memory-workflow.js:64-99 (registration)Tool registration of 'localnest_memory_recall' within 'registerMemoryWorkflowTools'.
registerJsonTool( ['localnest_memory_recall'], { title: 'Memory Recall', description: 'Recall the most relevant local memories for a task or query.', inputSchema: { query: z.string().min(1), root_path: z.string().optional(), project_path: z.string().optional(), branch_name: z.string().optional(), topic: z.string().optional(), feature: z.string().optional(), kind: MEMORY_KIND_SCHEMA.optional(), limit: z.number().int().min(1).max(50).default(10) }, annotations: { readOnlyHint: true, destructiveHint: false, idempotentHint: false, openWorldHint: false } }, async ({ query, root_path, project_path, branch_name, topic, feature, kind, limit }) => normalizeMemoryRecallResult( await memory.recall({ query, rootPath: root_path, projectPath: project_path, branchName: branch_name, topic, feature, kind, limit }), query ) );