# Memory Vault (oci · ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0)

Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.

- Trust score: 43/100 (low)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- oci · `ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0`: 43/100 (this document), [markdown](https://verifymcp.io/servers/mihaibuilds-memory-vault/ghcr-io-mihaibuilds-memory-vault-mcp-1-6-0.md), [page](https://verifymcp.io/servers/mihaibuilds-memory-vault/ghcr-io-mihaibuilds-memory-vault-mcp-1-6-0)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0`
- 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 2026-09-20.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
- **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 (MIT).
  - Actively maintained (last published 9 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 813 tokens (~101/item across 8 items; 6 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 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**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "purge_forgotten" implies "purge" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - 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).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Memory Vault MCP server?

Memory Vault runs locally as a container image, launched with docker run --rm -i ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add mihaibuilds-memory-vault -- docker run --rm -i ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0
```

### Cursor

```json
{
  "mcpServers": {
    "mihaibuilds-memory-vault": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mihaibuilds-memory-vault": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mihaibuilds-memory-vault -- docker run --rm -i ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mihaibuilds-memory-vault": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  mihaibuilds-memory-vault:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0"]
```

### Netclaw

```json
{
  "McpServers": {
    "mihaibuilds-memory-vault": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "mihaibuilds-memory-vault": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0"
      ]
    }
  }
}
```

## 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.

### 2026-09-18 (score 43, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-10 (score 39)

First indexed and scored.

## MCP tools (6)

### `recall` (~261 tokens)

Search your memories for information relevant to a query.

Returns chunks ranked by relevance using hybrid search (vector + full-text + RRF).
Uses query enrichment (keyword extraction + variation) for better recall.
Results are budgeted to fit within max_tokens to avoid flooding context.

Args:
    query: The search query — a question, topic, or keyword phrase.
    spaces: Filter to specific memory spaces (e.g. ["default", "projects"]).
            If omitted, searches all spaces.
    since: Only return memories after this date (ISO format, e.g. "2025-01-01").
    limit: Maximum number of results (default 10, max 50).
    max_tokens: Token budget for results (default 2000).
    ef_search: How much of the vector index to search, 1-1000. Omit to use
            the default (40). Raise it when a search should have found
            something and did not — better recall, slower query. Worth
            trying before concluding a memory is missing.

Input parameters:

- `ef_search`
- `limit` (integer)
- `max_tokens` (integer)
- `query` (string, required)
- `since`
- `spaces`

Output parameters:

- `result` (string)

### `remember` (~128 tokens)

Store a new memory in the system.

The text is embedded and stored as a searchable chunk.
Use this to save important information, decisions, or knowledge.

Args:
    text: The text content to remember.
    space: Which memory space to store it in (default "default").
    source: Where this memory comes from (default "mcp").
    speaker: Who said/wrote this — "human" or "assistant" (default "human").

Input parameters:

- `source` (string)
- `space` (string)
- `speaker` (string)
- `text` (string, required)

Output parameters:

- `result` (string)

### `forget` (~66 tokens)

Soft-delete a memory chunk by ID.

The chunk is removed from search results but stays in the database
for potential recovery. Sets importance to 0 and marks it in metadata.

Args:
    chunk_id: The UUID of the chunk to forget.

Input parameters:

- `chunk_id` (string, required)

Output parameters:

- `result` (string)

### `purge_forgotten` (~175 tokens)

Permanently delete memories that were forgotten a while ago.

\`forget` is a soft delete: the memory stops appearing in search but the row
stays, so it can be recovered. Nothing removed it afterwards, so a vault
that is edited often accumulated one dead row per edit forever.

This is the deliberate, irreversible half. It is never automatic — there is
no timer that quietly deletes your memories — and it only touches memories
already marked forgotten, never active ones.

Args:
    older_than_days: Only purge memories forgotten at least this many days
        ago. The default keeps a month of recovery, so purging right after
        an accidental forget still spares it. Pass 0 to purge every
        forgotten memory regardless of age.

Input parameters:

- `older_than_days` (integer)

Output parameters:

- `result` (string)

### `move_memory` (~120 tokens)

Move a stored memory into a different space.

The memory keeps its content and embedding; only the space it belongs to
changes. Its knowledge-graph entries are rebuilt in the target space so
the graph and search agree about where it lives.

The target space must already exist — use the dashboard or the API to
create one first.

Args:
    chunk_id: The UUID of the chunk to move.
    target_space: Name of the space to move it into.

Input parameters:

- `chunk_id` (string, required)
- `target_space` (string, required)

Output parameters:

- `result` (string)

### `memory_status` (~32 tokens)

Get the current status of the memory system.

Returns database health, chunk counts per space, and embedding model info.

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/mihaibuilds-memory-vault/ghcr-io-mihaibuilds-memory-vault-mcp-1-6-0#diagnostics

## Score history

- 2026-09-20: 43
- 2026-09-19: 43
- 2026-09-18: 43
- 2026-09-17: 39
- 2026-09-16: 39
- 2026-09-15: 39
- 2026-09-14: 39
- 2026-09-13: 39
- 2026-09-12: 39
- 2026-09-11: 39
- 2026-09-10: 39

## Common questions

### What is the Memory Vault MCP server?

Memory Vault is an MCP server listed in the public MCP registry as io.github.MihaiBuilds/memory-vault. Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT. This page covers its container image (ghcr.io/mihaibuilds/memory-vault-mcp:1.6.0).

### Is the Memory Vault MCP server safe to use?

Memory Vault scores 43 out of 100 on VerifyMCP. 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 Memory Vault MCP server expose?

Memory Vault exposes 6 tools: recall, remember, forget, purge_forgotten, move_memory, memory_status. Their descriptions and schemas cost roughly 782 tokens of context every time the server is loaded.

### Is the Memory Vault MCP server still maintained?

Memory Vault is still listed as active in the MCP registry. We last reached this channel on 20 September 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 Memory Vault MCP server under?

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

## Links

- Repository: https://github.com/MihaiBuilds/memory-vault
- Website: https://mihaibuilds.com/
- Changelog RSS feed: https://verifymcp.io/servers/mihaibuilds-memory-vault/ghcr-io-mihaibuilds-memory-vault-mcp-1-6-0.xml
- Changelog JSON feed: https://verifymcp.io/servers/mihaibuilds-memory-vault/ghcr-io-mihaibuilds-memory-vault-mcp-1-6-0.json
- HTML version of this page: https://verifymcp.io/servers/mihaibuilds-memory-vault/ghcr-io-mihaibuilds-memory-vault-mcp-1-6-0