Memory Box MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SYSTEM_PROMPT | No | Custom system prompt for formatting memories | |
| DEFAULT_BUCKET | No | The default bucket to use when saving memories | General |
| MEMORY_BOX_TOKEN | Yes | Your authentication token for Memory Box | |
| MEMORY_BOX_API_URL | No | The URL of your Memory Box instance | https://memorybox.amotivv.ai |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| save_memoryC | Save a memory to Memory Box |
| search_memoriesB | Search for memories using semantic search |
| get_all_memoriesC | Retrieve all memories with pagination support |
| get_bucket_memoriesC | Get memories from a specific bucket |
| get_related_memoriesC | Find semantically similar memories to a specific memory |
| check_memory_statusC | Check the processing status of a memory |
| get_usage_statsB | Retrieve user usage statistics and plan information |
| get_bucketsB | Retrieve a list of all available buckets |
| create_bucketC | Create a new bucket for organizing memories |
| delete_bucketA | Delete a bucket (empty by default, use force to delete with content) |
| update_memoryC | Update an existing memory including text, bucket, and relationships |
| delete_memoryC | Delete a specific memory |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Each tool has a clearly distinct purpose with no significant overlap. Tools target specific actions on distinct resources like memories, buckets, or system status, making it easy for an agent to select the right one. For example, get_all_memories vs. get_bucket_memories vs. search_memories are well-differentiated by scope and method.
All tool names follow a consistent verb_noun pattern using snake_case, such as create_bucket, delete_memory, and get_usage_stats. This uniformity makes the set predictable and easy to parse, with no deviations in style or convention across the 12 tools.
With 12 tools, the server is well-scoped for a memory management system, covering core operations without bloat. Each tool earns its place by addressing key needs like CRUD for memories and buckets, organization, search, and system monitoring, fitting typical expectations for such a domain.
The tool surface provides complete CRUD and lifecycle coverage for memories and buckets, including create, read, update, delete, search, and organization features. No obvious gaps exist; agents can perform all essential workflows from saving and retrieving memories to managing buckets and checking status.