Openmemory MCP Server

> **real long-term memory for ai agents. not rag. not a vector db. self-hosted.**

Remote serverstreamable-httpPython

What is the Openmemory MCP server?

real long-term memory for ai agents. not rag. not a vector db. self-hosted.. The openmemory mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 4 defined tools rather than through you.

What it actually does

Expect breaking changes and potential bugs. ### Contributers needed To contribute, visit https://github.com/CaviraOSS/OpenMemory/tree/rewrite branch. If you find an issue, please open a GitHub issue with details so it can be tracked and resolved. ## OpenMemory

Its toolset

Everything the assistant can do here goes through one of these:

  • Concepts — The Concepts tool exposed by this server
  • Example — Alice’s term is automatically closed; timeline queries stay sane
  • Usage — The Usage tool exposed by this server
  • Commands — Useful for scripting, debugging, and non‑LLM pipelines that still want memory

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration

You will need 2 environment variables: PINECONE_API_KEY, OPENAI_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.

When to reach for it

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Openmemory's toolset — Concepts, Example, Usage and 1 more — is a fair guide to whether it matches your workflow. It is maintained by nullure; 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.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • 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 openmemory mcp server does with a few real requests.

Available tools

ToolWhat it does
ConceptsThe Concepts tool exposed by this server.
ExampleAlice’s term is automatically closed; timeline queries stay sane.
UsageThe Usage tool exposed by this server.
CommandsUseful for scripting, debugging, and non‑LLM pipelines that still want memory.

How to install the Openmemory MCP server

### Cursor / Windsurf

`.mcp.json`:

```json
{
  "mcpServers": {
    "openmemory": {
      "type": "http",
      "url": "http://localhost:8080/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
PINECONE_API_KEYCredential the server authenticates with.Yes
OPENAI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Openmemory to Concepts.
  • Use Openmemory to Example.
  • Use Openmemory to Usage.

Frequently asked questions

It connects Openmemory to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Concepts, Example, Usage, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Openmemory directly.