# Polypack Memory (pypi · polypack-mcp)

MCP server exposing Polypack as persistent adaptive memory

- Trust score: 32/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-23

## Components

- pypi · `polypack-mcp`: 32/100 (this document), [markdown](https://verifymcp.io/servers/imattau-polypack-mcp/polypack-mcp.md), [page](https://verifymcp.io/servers/imattau-polypack-mcp/polypack-mcp)

## Channel facts

- Registry: `pypi`
- Package: `polypack-mcp`
- Version: `0.1.16`
- 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 2026-08-23.

- **Supply Chain Security**: 32/100
  - Malware scan not yet available for this package.
  - CVE check failed: a known high-severity CVE affects mcp 1.9.4, a direct dependency. A fixed version is available.
  - Runs setuptools.build_meta at install time, a recognised native-build step with no shell scripting around it.
  - 2 of 25 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**: 34/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 893 tokens (~55/item across 16 items; 12 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 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 Polypack Memory MCP server?

Polypack Memory runs locally as a PyPI package, launched with uvx polypack-mcp. 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 imattau-polypack-mcp -- uvx polypack-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "imattau-polypack-mcp": {
      "command": "uvx",
      "args": [
        "polypack-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "imattau-polypack-mcp": {
      "command": "uvx",
      "args": [
        "polypack-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add imattau-polypack-mcp -- uvx polypack-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add imattau-polypack-mcp --command uvx --arg polypack-mcp
```

### Hermes

```yaml
mcp_servers:
  imattau-polypack-mcp:
    command: "uvx"
    args: ["polypack-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "imattau-polypack-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "polypack-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add imattau-polypack-mcp -t stdio -c uvx -a polypack-mcp
```

### Other

```json
{
  "mcpServers": {
    "imattau-polypack-mcp": {
      "command": "uvx",
      "args": [
        "polypack-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-23 (score 32)

First indexed and scored.

## MCP tools (12)

### `memory_store` (~94 tokens)

Store durable project memory.

Use procedural for preferences, conventions, and decisions; semantic for
stable facts; episodic for events or task outcomes; and entity for named
people, projects, or objects. Use a stable context for project memory.

Input parameters:

- `confidence` (number)
- `content` (string, required)
- `context`
- `memory_class` (string)
- `metadata`
- `provenance`

### `memory_recall` (~162 tokens)

Search memories by text, context, activation, and confidence.

Use this for a targeted question. Use memory_context to assemble working
context. Context is soft by default; use strict_context=true for isolation.
With include_neighbors=true, bounded graph neighbors are hydrated into the
result. Filter relationships with edge_types such as RESPONDS_TO. The
neighbor_limit bounds hydrated neighbors; limit remains the total result
count. Metadata reports when additional neighbors were available.

Input parameters:

- `context`
- `depth` (integer)
- `edge_types`
- `include_neighbors` (boolean)
- `limit` (integer)
- `neighbor_limit` (integer)
- `query` (string, required)
- `strict_context` (boolean)
- `token_budget`

### `memory_thread` (~60 tokens)

Walk the RESPONDS_TO chain from a starting memory ID and return the thread.

Retrieves connected memories in both directions along RESPONDS_TO edges,
returning them sorted chronologically.

Input parameters:

- `max_depth` (integer)
- `start_id` (string, required)

### `memory_context` (~75 tokens)

Return a working-memory set selected by activation and estimated-token budget.

token_budget is an estimated-token budget. Each returned memory fits wholly
within the remaining budget; budgets must be greater than zero.

Input parameters:

- `context` (string, required)
- `limit` (integer)
- `strict_context` (boolean)
- `token_budget`

### `memory_feedback` (~54 tokens)

Record whether a retrieved memory helped this task.

Call this after using a recalled memory when it was useful or misleading.

Input parameters:

- `agent_id` (string)
- `memory_id` (string, required)
- `useful` (boolean, required)

### `memory_suppress` (~37 tokens)

Inhibit a stale or unhelpful memory without deleting it.

Input parameters:

- `amount` (number)
- `memory_id` (string, required)

### `memory_supersede` (~37 tokens)

Replace an outdated fact while retaining its history.

Input parameters:

- `new_memory_id` (string, required)
- `old_memory_id` (string, required)

### `memory_consolidate` (~56 tokens)

Consolidate source memories into one durable higher-level memory.

Input parameters:

- `confidence` (number)
- `content` (string, required)
- `context`
- `memory_class` (string)
- `source_ids` (array, required)

### `memory_link` (~80 tokens)

Connect two memories with an explicit graph relationship.

Use RESPONDS_TO when a new handoff, verification, or fix addresses an
earlier memory. Use memory_recall(include_neighbors=true) to retrieve
linked memories with relationship metadata.

Input parameters:

- `relationship` (string)
- `source_memory_id` (string, required)
- `target_memory_id` (string, required)

### `memory_store_batch` (~63 tokens)

Store multiple durable project memories in a single batch.

Each item in the list should be a dict with 'content' and optional
'memory_class', 'context', 'confidence', 'provenance', and 'metadata' keys.

Input parameters:

- `memories` (array, required)

### `memory_link_batch` (~65 tokens)

Connect multiple pairs of memories with explicit graph relationships in a single batch.

Each item in the list should be a dict with 'source_memory_id', 'target_memory_id',
and optional 'relationship' (defaults to 'RESPONDS_TO') keys.

Input parameters:

- `links` (array, required)

### `graph_query` (~89 tokens)

Inspect graph neighbors/schema or perform an advanced edge operation.

Prefer memory_link for normal memory relationships. Supported operations
are neighbors, add_edge, schema, and relationship_diagnostics. RESPONDS_TO
graph edges are authoritative; diagnostics identifies legacy
provenance-only relationships.

Input parameters:

- `id`
- `operation` (string, required)
- `source`
- `target`
- `type`

## Diagnostics

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

## Score history

- 2026-08-23: 32

## Common questions

### What is the Polypack Memory MCP server?

Polypack Memory is an MCP server listed in the public MCP registry as io.github.imattau/polypack-mcp. MCP server exposing Polypack as persistent adaptive memory. This page covers its PyPI package (polypack-mcp).

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

Polypack Memory scores 32 out of 100 on VerifyMCP. We recorded 8 known advisories against it as of 23 August 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 Polypack Memory MCP server expose?

Polypack Memory exposes 12 tools: memory_store, memory_recall, memory_thread, memory_context, memory_feedback, and 7 more. Their descriptions and schemas cost roughly 872 tokens of context every time the server is loaded.

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

Polypack Memory is still listed as active in the MCP registry. We last reached this channel on 23 August 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/polypack-mcp/
- Socket report: https://socket.dev/pypi/package/polypack-mcp
- Repository: https://github.com/imattau/polypack-mcp
- Changelog RSS feed: https://verifymcp.io/servers/imattau-polypack-mcp/polypack-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/imattau-polypack-mcp/polypack-mcp.json
- HTML version of this page: https://verifymcp.io/servers/imattau-polypack-mcp/polypack-mcp