AI Memory MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| store_memoryB | Store a new memory or piece of knowledge. Use this to remember important information, facts, preferences, or context for future conversations. |
| search_memoriesC | Search through stored memories using keywords or tags. Returns relevant memories that match the search criteria. |
| list_memoriesC | List all stored memories with optional filtering by tags. |
| delete_memoryC | Delete a specific memory by its ID. |
| clear_memoriesA | Clear all stored memories. Use with caution as this cannot be undone. |
| get_memory_statsB | Get statistics about stored memories (total count, tags, etc.) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| All Memories | Complete list of all stored memories |
| Memory Statistics | Statistics about stored memories |
TDQS
Scored across 6 tools
Each tool has a clearly distinct purpose with no overlap: clear_memories removes all memories, delete_memory targets a specific ID, get_memory_stats provides metadata, list_memories enumerates with filtering, search_memories finds matches based on content, and store_memory adds new data. An agent can easily distinguish between these operations.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., clear_memories, delete_memory, store_memory). The verbs are precise and descriptive, making the set highly predictable and readable.
With 6 tools, the server is well-scoped for an AI memory management system. Each tool serves a distinct role in the memory lifecycle (store, retrieve, search, manage, and analyze), and none feel redundant or missing for the domain.
The toolset provides complete CRUD/lifecycle coverage for memory management: store_memory (create), list_memories/search_memories (read/query), delete_memory (delete), clear_memories (bulk delete), and get_memory_stats (analytics). There are no obvious gaps that would hinder an agent's workflow.