A MCP Server

Self-evolving memory system for AI agents

Local serverstdioPython

What is the A MCP server?

A MCP server is a locally run integration for AI assistants that speak the Model Context Protocol. Self-evolving memory system for AI agents.

What you get

A-MEM is a self-evolving memory system for coding agents. Unlike simple vector stores, A-MEM automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships. Memories don't just get stored—they evolve and connect over time.

What the assistant can call

Once A is connected, these are the calls the assistant has available:

  • add_memory_note — Store new knowledge (async, returns immediately)
  • search_memories — Semantic search across all memories
  • search_memories_agentic — Search + follow graph connections
  • search_memories_by_time — Search within a time range
  • read_memory_note — Get full details (supports bulk reads)
  • update_memory_note — Modify existing memory
  • delete_memory_note — Remove a memory
  • check_task_status — Check async task completion
  • Uninstall — The Uninstall tool exposed by this server

Setting it up

a-mem on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Configuration and credentials

You will need 5 environment variables: LLM_BACKEND, LLM_MODEL, OPENAI_API_KEY, CHROMA_DB_PATH, OPENROUTER_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Choosing this one

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. A's toolset — add_memory_note, search_memories, search_memories_agentic and 6 more — is a fair guide to whether it matches your workflow. It is maintained by DiaaAj; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 9 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch A.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the a mcp server does with a few real requests.

Available tools

ToolWhat it does
add_memory_noteStore new knowledge (async, returns immediately)
search_memoriesSemantic search across all memories
search_memories_agenticSearch + follow graph connections
search_memories_by_timeSearch within a time range
read_memory_noteGet full details (supports bulk reads)
update_memory_noteModify existing memory
delete_memory_noteRemove a memory
check_task_statusCheck async task completion
UninstallThe Uninstall tool exposed by this server.

How to install the A MCP server

{
  "mcpServers": {
    "a-mem": {
      "command": "uvx",
      "args": ["a-mem"],
      "env": {
        "LLM_BACKEND": "your-value",
        "LLM_MODEL": "your-value",
        "OPENAI_API_KEY": "your-value",
        "CHROMA_DB_PATH": "your-value",
        "OPENROUTER_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
LLM_BACKENDConfiguration value read at startup.Optional
LLM_MODELConfiguration value read at startup.Optional
OPENAI_API_KEYCredential the server authenticates with.Yes
CHROMA_DB_PATHFilesystem location the server is allowed to use.Optional
OPENROUTER_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use A to add memory note.
  • Use A to search memories.
  • Use A to search memories agentic.

Frequently asked questions

It connects A to MCP-compatible AI assistants such as Claude and Cursor, exposing 9 tools (add_memory_note, search_memories, search_memories_agentic, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with A directly.