# OpenMyMemo (pypi · openmymemo)

Your AI memory as a local folder you own. Every app shares it; you see and can undo each change.

- Trust score: 54/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- pypi · `openmymemo`: 54/100 (this document), [markdown](https://verifymcp.io/servers/mymemoai-openmymemo/openmymemo.md), [page](https://verifymcp.io/servers/mymemoai-openmymemo/openmymemo)

## Channel facts

- Registry: `pypi`
- Package: `openmymemo`
- Version: `0.2.6`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 4 of 42 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 72/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 859 tokens (~143/item across 6 items; 5 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 7/100
  - Stability observed for 2 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the OpenMyMemo MCP server?

OpenMyMemo runs locally as a PyPI package, launched with uvx openmymemo. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add mymemoai-openmymemo -- uvx openmymemo
```

### Cursor

```json
{
  "mcpServers": {
    "mymemoai-openmymemo": {
      "command": "uvx",
      "args": [
        "openmymemo"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mymemoai-openmymemo": {
      "command": "uvx",
      "args": [
        "openmymemo"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mymemoai-openmymemo -- uvx openmymemo
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mymemoai-openmymemo": {
      "type": "local",
      "command": [
        "uvx",
        "openmymemo"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mymemoai-openmymemo --command uvx --arg openmymemo
```

### Hermes

```yaml
mcp_servers:
  mymemoai-openmymemo:
    command: "uvx"
    args: ["openmymemo"]
```

### Netclaw

```json
{
  "McpServers": {
    "mymemoai-openmymemo": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "openmymemo"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mymemoai-openmymemo -t stdio -c uvx -a openmymemo
```

### Other

```json
{
  "mcpServers": {
    "mymemoai-openmymemo": {
      "command": "uvx",
      "args": [
        "openmymemo"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-17 (score 54, 0)

- [security improvement] Malware scan: unverified → pass
- [functional] Package version: 0.2.5 → 0.2.6

### 2026-10-16 (score 54, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.2.4 → 0.2.5

### 2026-10-15 (score 53)

First indexed and scored.

## MCP tools (5)

### `memory_context` (~78 tokens)

Read memory

Get the user's memory as Markdown: who they are, how they want you to work, what they're doing.

Call this once at the start of a conversation. `topics` limits it to some topic slugs;
\`max_chars` caps its length (most important memories come first).

Input parameters:

- `max_chars` (integer)
- `topics`

Output parameters:

- `result` (string)

### `memory_search` (~44 tokens)

Search memory

Search the user's memory by keywords (any language). Returns matching memories with their ids.

Input parameters:

- `limit` (integer)
- `query` (string, required)
- `topics`

### `memory_get` (~31 tokens)

Get memories

Fetch specific memories by id, with their topic, kind, source and timestamps.

Input parameters:

- `ids` (array, required)

### `memory_propose` (~329 tokens)

Propose a memory change

Add, correct or retire a memory of the user's. Returns at once; it never waits for the user.

\- op="add": `content` is one self-contained statement about the user, written in the third person
  or as the user would say it (e.g. "Prefers answers in Chinese"). Optional `topic` is a topic slug
  from memory_context; leave it out to let OpenMyMemo file it.
\- op="update": `memory_id` plus the full corrected `content`.
\- op="archive": `memory_id` of a memory that is no longer true.
\`reason` says why; `evidence` quotes what the user said. Reuse an `idempotency_key` when retrying.

Returns `status`:
\- "applied": saved now. The user sees it in their OpenMyMemo digest and can undo it.
\- "pending": waiting for the user, and `hold` says why: "protected" (they wrote that memory
  themselves), "private" (it is in a private topic) or "approval" (they review every change first).
\- "duplicate": they already have this memory; nothing was saved.
An add that resembles an existing memory becomes an update of that memory (see `note`).
Don't ask the user to approve anything in the chat.

Input parameters:

- `content`
- `evidence`
- `idempotency_key`
- `kind`
- `memory_id`
- `op` (string, required)
- `reason`
- `topic`

### `memory_proposals` (~114 tokens)

Check proposed changes

List the proposals this app made and what happened to them, so you don't repeat rejected or undone ones.

Statuses: applied (saved; the user may still undo it), pending (waiting for the user; `hold` says
why), accepted or edited_accepted (the user approved it, perhaps reworded), rejected, undone, expired.
A proposal that waited in MyMemo Cloud's offline queue also has the `queue_id` it was given then.

Input parameters:

- `limit` (integer)
- `status`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/mymemoai-openmymemo/openmymemo#diagnostics

## Score history

- 2026-10-17: 54
- 2026-10-16: 54
- 2026-10-15: 53

## Common questions

### What is the OpenMyMemo MCP server?

OpenMyMemo is an MCP server listed in the public MCP registry as io.github.MyMemoAI/openmymemo. Your AI memory as a local folder you own. Every app shares it; you see and can undo each change. This page covers its PyPI package (openmymemo).

### Is the OpenMyMemo MCP server safe to use?

OpenMyMemo scores 54 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the OpenMyMemo MCP server expose?

OpenMyMemo exposes 5 tools: memory_context, memory_search, memory_get, memory_propose, memory_proposals. Their descriptions and schemas cost roughly 596 tokens of context every time the server is loaded.

### Is the OpenMyMemo MCP server still maintained?

OpenMyMemo is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the OpenMyMemo MCP server under?

OpenMyMemo declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/openmymemo/
- Socket report: https://socket.dev/pypi/package/openmymemo
- Repository: https://github.com/MyMemoAI/openmymemo
- Changelog RSS feed: https://verifymcp.io/servers/mymemoai-openmymemo/openmymemo.xml
- Changelog JSON feed: https://verifymcp.io/servers/mymemoai-openmymemo/openmymemo.json
- HTML version of this page: https://verifymcp.io/servers/mymemoai-openmymemo/openmymemo