# memory-boost (pypi · memory-boost)

Markdown memory for coding agents that audits itself: drift reports and session digests.

- Trust score: 87/100 (high trust)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- pypi · `memory-boost`: 87/100 (this document), [markdown](https://verifymcp.io/servers/arnaugonzalez-memory-boost/memory-boost.md), [page](https://verifymcp.io/servers/arnaugonzalez-memory-boost/memory-boost)

## Channel facts

- Registry: `pypi`
- Package: `memory-boost`
- Version: `0.1.1`
- 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 2026-10-16.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - 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.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to arnaugonzalez/memory-boost).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 19 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 762 tokens (~95/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 67/100
  - Stability observed for 20 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 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 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 memory-boost MCP server?

memory-boost runs locally as a PyPI package, launched with uvx memory-boost. 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 arnaugonzalez-memory-boost -- uvx memory-boost
```

### Cursor

```json
{
  "mcpServers": {
    "arnaugonzalez-memory-boost": {
      "command": "uvx",
      "args": [
        "memory-boost"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "arnaugonzalez-memory-boost": {
      "command": "uvx",
      "args": [
        "memory-boost"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add arnaugonzalez-memory-boost -- uvx memory-boost
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add arnaugonzalez-memory-boost --command uvx --arg memory-boost
```

### Hermes

```yaml
mcp_servers:
  arnaugonzalez-memory-boost:
    command: "uvx"
    args: ["memory-boost"]
```

### Netclaw

```json
{
  "McpServers": {
    "arnaugonzalez-memory-boost": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "memory-boost"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add arnaugonzalez-memory-boost -t stdio -c uvx -a memory-boost
```

### Other

```json
{
  "mcpServers": {
    "arnaugonzalez-memory-boost": {
      "command": "uvx",
      "args": [
        "memory-boost"
      ]
    }
  }
}
```

## 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.

### 2026-10-16 (score 87, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-14 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 71, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-12 (score 86, +18)

- [security improvement] Malware scan: unverified → pass

### 2026-10-06 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 33. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-04 (score 67, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-09-28 (score 63, +10)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-09-27 (score 53, −15)

- [security regression] Malware scan: pass → unverified

## MCP tools (8)

### `memory_brief` (~81 tokens)

Cheap orientation (~1k tokens): wiki catalog, the project's stable context and
its latest sessions. Call it at the start of a session in harnesses without a
SessionStart hook, or to reload a project's context mid-session. `project` is a
project name or a directory path.

Input parameters:

- `budget` (integer)
- `project`

Output parameters:

- `result` (string)

### `memory_recall` (~83 tokens)

Full-text search over wiki pages and log entries. Each hit is tagged
[kind | date | freshness]; current knowledge is listed before historic and
superseded. Historic hits are omitted unless include_historic=true.

Input parameters:

- `include_historic` (boolean)
- `limit` (integer)
- `project`
- `query` (string, required)

Output parameters:

- `result` (string)

### `memory_page` (~60 tokens)

Read a wiki page by name (e.g. 'my-api'), or one section of it (a heading or
the anchor returned by memory_recall). Prefer this over reading the whole file.

Input parameters:

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

Output parameters:

- `result` (string)

### `memory_save` (~113 tokens)

Record what was done in a session: one raw JSONL event plus one compiled entry
in wiki/log.md (creates the project page if it does not exist yet). `action` is a
one-line summary; `detail` a longer bullet; `pending` what is left to do.
Does not commit anything to git.

Input parameters:

- `action` (string, required)
- `agent` (string)
- `detail`
- `pending`
- `project` (string, required)
- `result` (string)

Output parameters:

- `result` (string)

### `memory_checkpoint` (~173 tokens)

Save this session's working state (a small JSON, no indexing) so it survives
context compaction and parallel sessions on the same project can see it. Call it
after each milestone: task = current goal (1 line), done = finished steps
(accumulated), next_step = the concrete next step, files = files touched.
session_id: the `checkpoint_session=` value injected at session start, or any
stable id. Set status=done when the session ends (after memory_save).

Input parameters:

- `agent` (string)
- `done`
- `files`
- `next_step`
- `notes`
- `plan_ref`
- `project` (string, required)
- `session_id` (string, required)
- `status` (string)
- `task` (string, required)

Output parameters:

- `result` (string)

### `memory_resume` (~65 tokens)

Return this session's checkpoint (if session_id is given) plus one line per
other active session on the project. Use after a compaction or when picking up
unfinished work; much cheaper than memory_recall.

Input parameters:

- `project` (string, required)
- `session_id`

Output parameters:

- `result` (string)

### `memory_drift` (~64 tokens)

What in the memory has drifted: decisions past review_by, superseded decisions
without a successor, project pages with no session for weeks, busy projects with no
recorded decisions, checkpoints left open. Whole wiki, or one project's findings.

Input parameters:

- `project`

Output parameters:

- `result` (string)

### `memory_lesson` (~123 tokens)

Record a lesson that should reach other projects: what worked (or failed), the
tools involved and when it applies. `applies_when` are stack/situation tags
(e.g. ["fastapi", "celery", "e2e-tests"]); projects whose page lists matching
\`tags:` get this lesson in their session brief. `learned_on` = this project's slug.

Input parameters:

- `applies_when` (array, required)
- `body` (string, required)
- `learned_on`
- `name` (string, required)
- `title` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

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

## Score history

- 2026-10-16: 87
- 2026-10-15: 72
- 2026-10-14: 72
- 2026-10-13: 71
- 2026-10-12: 86
- 2026-10-06: 68
- 2026-10-04: 67
- 2026-10-03: 63
- 2026-10-02: 63
- 2026-10-01: 63
- 2026-09-30: 63
- 2026-09-29: 63
- 2026-09-28: 63
- 2026-09-27: 53
- 2026-09-26: 68

## Common questions

### What is the memory-boost MCP server?

memory-boost is an MCP server listed in the public MCP registry as io.github.arnaugonzalez/memory-boost. Markdown memory for coding agents that audits itself: drift reports and session digests. This page covers its PyPI package (memory-boost).

### Is the memory-boost MCP server safe to use?

memory-boost scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. Its build provenance is signed and verified. 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-boost MCP server expose?

memory-boost exposes 8 tools: memory_brief, memory_recall, memory_page, memory_save, memory_checkpoint, and 3 more. Their descriptions and schemas cost roughly 762 tokens of context every time the server is loaded.

### Is the memory-boost MCP server still maintained?

memory-boost is still listed as active in the MCP registry. We last reached this channel on 16 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 memory-boost MCP server under?

memory-boost 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

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