# Turbo Quant Memory (pypi · turbo-quant-memory)

Local-first memory and knowledge graph for coding agents. Compact retrieval, no network.

- Trust score: 56/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- pypi · `turbo-quant-memory`: 56/100 (this document), [markdown](https://verifymcp.io/servers/lexus2016-turbo-quant-memory/turbo-quant-memory.md), [page](https://verifymcp.io/servers/lexus2016-turbo-quant-memory/turbo-quant-memory)

## Channel facts

- Registry: `pypi`
- Package: `turbo-quant-memory`
- Version: `0.29.1`
- 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**: 82/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects cryptography 46.0.7, a direct dependency. A fixed version is available.
  - Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it.
  - 16 of 92 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: no license is declared.
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 1653 tokens (~87/item across 19 items; 19 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 13/100
  - Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 47/100
  - 58% 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 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "unlink_entities" implies "unlink" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 20 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Turbo Quant Memory MCP server?

Turbo Quant Memory runs locally as a PyPI package, launched with uvx turbo-quant-memory. 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 lexus2016-turbo-quant-memory -- uvx turbo-quant-memory
```

### Cursor

```json
{
  "mcpServers": {
    "lexus2016-turbo-quant-memory": {
      "command": "uvx",
      "args": [
        "turbo-quant-memory"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "lexus2016-turbo-quant-memory": {
      "command": "uvx",
      "args": [
        "turbo-quant-memory"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add lexus2016-turbo-quant-memory -- uvx turbo-quant-memory
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lexus2016-turbo-quant-memory": {
      "type": "local",
      "command": [
        "uvx",
        "turbo-quant-memory"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add lexus2016-turbo-quant-memory --command uvx --arg turbo-quant-memory
```

### Hermes

```yaml
mcp_servers:
  lexus2016-turbo-quant-memory:
    command: "uvx"
    args: ["turbo-quant-memory"]
```

### Netclaw

```json
{
  "McpServers": {
    "lexus2016-turbo-quant-memory": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "turbo-quant-memory"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add lexus2016-turbo-quant-memory -t stdio -c uvx -a turbo-quant-memory
```

### Other

```json
{
  "mcpServers": {
    "lexus2016-turbo-quant-memory": {
      "command": "uvx",
      "args": [
        "turbo-quant-memory"
      ]
    }
  }
}
```

## 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.

### 2026-09-20 (score 56, +2)

- [functional improvement] Stability: unverified → 0.13
- [functional] Package version: 0.28.3 → 0.29.1

### 2026-09-18 (score 54, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-17 (score 39, −15)

- [security regression] Malware scan: pass → unverified

### 2026-09-16 (score 54)

First indexed and scored.

## MCP tools (19)

### `health` (~4 tokens)

### `server_info` (~5 tokens)

### `list_scopes` (~6 tokens)

### `self_test` (~5 tokens)

### `remember_note` (~363 tokens)

Store a typed project note. kind must be exactly one of: lesson, decision, pattern, handoff.

tags: 2-3 lowercase tags are strongly recommended — tags are the only way
  to FILTER notes; an untagged note is reachable by semantic_search alone.
source_refs: the files / notes / issues this note is about. Pass them as
  entity URIs (note://<id>, file://<relative/path>, issue://KEY,
  https://...) and they are auto-linked into the knowledge graph as
  \`references` relations, so get_related_entities can later surface them.
provenance: who originated the note. Use "human-explicit" when the USER
  asked to remember something ("remember this", "save that"); "agent" for
  your own observations (the default); "external-tool" for API/tool data;
  "system" for automatic processes.
tier: normally derived from `kind` (handoff -> episodic, every other kind
  \-> durable). Override e.g. tier="durable" to keep a `handoff` in the
  default-searchable set, or tier="episodic" to keep a noisy lesson out of
  regular search.

After storing, connect the note with link_entities(source_uri="note://<id>",
...) when it relates to a file, issue, or prior note — the response echoes
the note's uri and hints this when the note still has no relations.

Input parameters:

- `content` (string, required)
- `kind` (string, required)
- `provenance` (string)
- `scope` (string)
- `source_refs`
- `tags`
- `tier`
- `title` (string, required)

### `promote_note` (~13 tokens)

Input parameters:

- `note_id` (string, required)

### `deprecate_note` (~40 tokens)

Input parameters:

- `note_id` (string, required)
- `reason`
- `replacement_note_id`
- `replacement_scope`
- `scope` (string)

### `semantic_search` (~239 tokens)

Compact memory retrieval (dense vector + BM25, fused via RRF).

By default only the `durable` and `reference` tiers are searched, so
session `handoff` notes (which live in the `episodic` tier) are NOT
returned. To recover handoffs / session summaries pass
\``tier_filter=["episodic"]`` (or list every tier to opt everything in).
For a query-free "where did I leave off" bootstrap at session start,
prefer the `recent_context` tool instead.

source_filter narrows results by source type: ``"notes"`` returns only
memory notes (decisions/lessons/patterns/handoffs), ``"markdown"`` only
indexed doc blocks. In doc-heavy projects the reference blocks often
crowd notes out of the top ranks on question-shaped queries — when you
are asking "what did we decide/learn about X", pass
\``source_filter="notes"``.

Input parameters:

- `limit` (integer)
- `query` (string, required)
- `scope` (string)
- `source_filter`
- `tier_filter`

### `hydrate` (~26 tokens)

Input parameters:

- `item_id` (string, required)
- `mode` (string)
- `scope` (string, required)

### `index_paths` (~94 tokens)

Register and index Markdown directories into project memory.

Supports .tqmemoryignore files (placed in project root or any indexed
directory) with glob patterns to exclude paths from indexing.
One pattern per line, # for comments.  Example patterns:
\``workspace-*`` skips any directory matching the glob;
\``data/reports/*.md`` skips files matching a path pattern.

Input parameters:

- `mode` (string)
- `paths`

### `lint_knowledge_base` (~21 tokens)

Input parameters:

- `max_issues` (integer)
- `paths`

### `link_entities` (~100 tokens)

Create a Knowledge Graph link between two entities.

Entities are specified using URIs:
  \- Note: note://<note_id>
  \- File: file://<relative_path> (relative to project root)
  \- External: e.g. issue://BUG-404, task://TASK-101

Input parameters:

- `relation_type` (string, required)
- `scope` (string)
- `source_uri` (string, required)
- `target_uri` (string, required)

### `unlink_entities` (~79 tokens)

Remove a Knowledge Graph link between two entities.

source_uri / target_uri use the same URI forms as link_entities:
note://<note_id>, file://<relative/path>, issue://KEY, https://...

Input parameters:

- `relation_type`
- `scope` (string)
- `source_uri` (string, required)
- `target_uri` (string, required)

### `get_related_entities` (~92 tokens)

Query relations involving a specific entity URI.

uri: the entity to look up, as note://<note_id>, file://<relative/path>,
issue://KEY, task://KEY, or https://... — the same URI forms link_entities
accepts. Returns nothing for an entity that has no links yet.

Input parameters:

- `relation_type`
- `scope` (string)
- `uri` (string, required)

### `set_secret` (~122 tokens)

Store an encrypted secret in the active project's vault.

The value is encrypted with AES-256-GCM under a per-project master
key resolved from TQMEMORY_SECRETS_PASSPHRASE or the OS keyring.
Secrets are NEVER indexed, embedded, or returned via
\``semantic_search`` / ``hydrate``. They live in
\``~/.turbo-quant-memory/projects/<project_id>/secrets/vault.tqv``
and stay on this machine.

Input parameters:

- `name` (string, required)
- `value` (string, required)

### `get_secret` (~84 tokens)

Fetch a project secret by exact name.

Returns the value in a dedicated ``secret_value`` field (never in
descriptive text). Status is ``"ok"`` on hit, ``"missing"`` when
no such name exists, or ``"error"`` with ``setup_hint`` when no
master key is configured yet.

Input parameters:

- `name` (string, required)

### `list_secrets` (~21 tokens)

List secret names in the active project. Never returns values.

### `delete_secret` (~23 tokens)

Delete a project secret by exact name.

Input parameters:

- `name` (string, required)

### `recent_context` (~180 tokens)

Query-free session bootstrap: the most recently updated notes.

Call this FIRST when starting a new session or resuming after a context
compaction, when you do not yet know what to search for. Returns notes
ordered by recency (newest first), NOT by relevance — including
\`handoff` notes (episodic tier), which a plain semantic_search hides by
default. This is the reliable "where did I leave off" entry point.

scope: 'project' (default), 'global', or 'hybrid'. Use 'hybrid' to also
surface promoted cross-project knowledge.
tier_filter: defaults to all tiers (so handoffs are included). Pass e.g.
["durable"] to exclude episodic session notes.

Input parameters:

- `limit` (integer)
- `scope` (string)
- `tier_filter`

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/lexus2016-turbo-quant-memory/turbo-quant-memory#diagnostics

## Score history

- 2026-09-20: 56
- 2026-09-19: 54
- 2026-09-18: 54
- 2026-09-17: 39
- 2026-09-16: 54

## Common questions

### What is the Turbo Quant Memory MCP server?

Turbo Quant Memory is an MCP server listed in the public MCP registry as io.github.Lexus2016/turbo-quant-memory. Local-first memory and knowledge graph for coding agents. Compact retrieval, no network. This page covers its PyPI package (turbo-quant-memory).

### Is the Turbo Quant Memory MCP server safe to use?

Turbo Quant Memory scores 56 out of 100 on VerifyMCP. We recorded 7 known advisories against it as of 20 September 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 Turbo Quant Memory MCP server expose?

Turbo Quant Memory exposes 19 tools: health, server_info, list_scopes, self_test, remember_note, and 14 more. Their descriptions and schemas cost roughly 1,517 tokens of context every time the server is loaded.

### Is the Turbo Quant Memory MCP server still maintained?

Turbo Quant Memory 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.

## Links

- PyPI project: https://pypi.org/project/turbo-quant-memory/
- Socket report: https://socket.dev/pypi/package/turbo-quant-memory
- Repository: https://github.com/Lexus2016/turbo_quant_memory
- Changelog RSS feed: https://verifymcp.io/servers/lexus2016-turbo-quant-memory/turbo-quant-memory.xml
- Changelog JSON feed: https://verifymcp.io/servers/lexus2016-turbo-quant-memory/turbo-quant-memory.json
- HTML version of this page: https://verifymcp.io/servers/lexus2016-turbo-quant-memory/turbo-quant-memory