Agenticmemory MCP Server

Persistent memory for AI agents — history, context, semantic search, queues. 17 tools, stdio/SSE.

Remote serverstreamable-httpPython

What is the Agenticmemory MCP server?

Most knowledge and memory work still happens through a UI a human drives. Agenticmemory MCP server moves it into the conversation instead. Persistent memory for AI agents — history, context, semantic search, queues. 17 tools, stdio/SSE.

The short version

Your agent writes great code all day — then forgets every decision the moment its context window resets. So you become the memory layer: re-explaining the project, the preferences, what broke last time. Agentic Memory is the memory your agent runs itself: one install, and it stores, recalls, and searches its own state across sessions, machines, and even other agents. It can even sign itself up — one command returns a working API key, no browser, no human.

  • Conversation history — — ordered, role-aware messages with recency windowing, sub-ms reads
  • Key-value context — — typed durable facts: decisions, preferences, runbooks
  • Long-term entries — — titled, tagged knowledge that survives months, with auto-summarisation
  • Entities — — people and systems the agent should know about
  • Scratchpad — — ephemeral working memory with TTLs (expiry is a feature)
  • Semantic search — — across everything the agent has ever stored

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

The tools it exposes

The server publishes 10 tools. What each one is for:

  • Key — value context** — typed durable facts: decisions, preferences, runbooks
  • Long — term entries** — titled, tagged knowledge that survives months, with auto-summarisation
  • Entities — people and systems the agent should know about
  • Scratchpad — ephemeral working memory with TTLs (expiry is a feature)
  • Bootstrap — full session context in one call
  • Queues — FIFO agent bus with long-poll and dead-letter, agmry queue (exit 2 = empty)
  • Multi — agent spaces** — a fleet of agents reads and writes one memory
  • End-to — end encryption** — zero-knowledge spaces where only you hold the key (agmry key generate)
  • Export — full data takeout per space, one command (agmry space export)
  • Multi-agent — Shared spaces across agents

What it needs from you

Configuration is passed through the environment: AGMRY_API_KEY, YOUR_API_KEY, AGMRY_ENCRYPTION_KEY, AGENTICMEMORY_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 10 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Agenticmemory.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

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. Agenticmemory's toolset — Key, Long, Entities and 7 more — is a fair guide to whether it matches your workflow. It is maintained by jyswee; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agenticmemory's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
Keyvalue context** — typed durable facts: decisions, preferences, runbooks
Longterm entries** — titled, tagged knowledge that survives months, with auto-summarisation
Entitiespeople and systems the agent should know about
Scratchpadephemeral working memory with TTLs (expiry is a feature)
Bootstrapfull session context in one call
QueuesFIFO agent bus with long-poll and dead-letter, agmry queue (exit 2 = empty)
Multiagent spaces** — a fleet of agents reads and writes one memory
End-toend encryption** — zero-knowledge spaces where only you hold the key (agmry key generate)
Exportfull data takeout per space, one command (agmry space export)
Multi-agentShared spaces across agents

How to install the Agenticmemory MCP server

{
  "mcpServers": {
    "agenticmemory": {
      "command": "npx",
      "args": ["-y", "agmry"],
      "env": {
        "AGMRY_API_KEY": "your-value",
        "YOUR_API_KEY": "your-value",
        "AGMRY_ENCRYPTION_KEY": "your-value",
        "AGENTICMEMORY_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
AGMRY_API_KEYCredential the server authenticates with.Yes
YOUR_API_KEYCredential the server authenticates with.Yes
AGMRY_ENCRYPTION_KEYCredential the server authenticates with.Yes
AGENTICMEMORY_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Agenticmemory to Key.
  • Use Agenticmemory to Long.
  • Use Agenticmemory to Entities.

Frequently asked questions

It connects Agenticmemory to MCP-compatible AI assistants such as Claude and Cursor, exposing 10 tools (Key, Long, Entities, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agenticmemory directly.