# Memory Hive (pypi · memory-hive-mcp)

Local-first memory over MCP. Built-in SQLite store; runs standalone. Agents propose; you confirm.

- Trust score: 62/100 (medium)
- Change this week: −12
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `memory-hive-mcp`: 62/100 (this document), [markdown](https://verifymcp.io/servers/330899935-hive-memory/memory-hive-mcp.md), [page](https://verifymcp.io/servers/330899935-hive-memory/memory-hive-mcp)

## Channel facts

- Registry: `pypi`
- Package: `memory-hive-mcp`
- Version: `0.1.9`
- 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 2026-11-04.

- **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 setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 74/100
  - Repository check failed: the declared repository URL redirects; it must resolve directly.
  - Cryptographically verified build provenance (signed, bound to 330899935/memory-hive-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 9 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1376 tokens (~229/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 43/100
  - Stability observed for 13 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 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**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

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

Memory Hive runs locally as a PyPI package, launched with uvx memory-hive-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 330899935-hive-memory -- uvx memory-hive-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "330899935-hive-memory": {
      "command": "uvx",
      "args": [
        "memory-hive-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "330899935-hive-memory": {
      "command": "uvx",
      "args": [
        "memory-hive-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add 330899935-hive-memory -- uvx memory-hive-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "330899935-hive-memory": {
      "type": "local",
      "command": [
        "uvx",
        "memory-hive-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add 330899935-hive-memory --command uvx --arg memory-hive-mcp
```

### Hermes

```yaml
mcp_servers:
  330899935-hive-memory:
    command: "uvx"
    args: ["memory-hive-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "330899935-hive-memory": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "memory-hive-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add 330899935-hive-memory -t stdio -c uvx -a memory-hive-mcp
```

### Other

```json
{
  "mcpServers": {
    "330899935-hive-memory": {
      "command": "uvx",
      "args": [
        "memory-hive-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.

### 2026-11-03 (score 62, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 61, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-01 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 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.

### 2026-10-31 (score 75, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-30 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 59, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-27 (score 74, +11)

- [security regression] Source repository: pass → fail
- [security improvement] Malware scan: unverified → pass

### 2026-10-26 (score 63, −15)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 0.1.8 → 0.1.9

## MCP tools (6)

### `recall` (~310 tokens)

Recall memory

Search the human's confirmed memory by natural-language query and return the closest stored entries. Use this to find what was previously decided, recorded, or agreed. Do not use it at session start when you have no query yet - use get_context instead. Do not use it to review entries still awaiting approval - use manage with action list_pending. Annotations already declare this read-only, so this text covers what they cannot: results come from the confirmed store only, private vaults are omitted for agents not permitted to read them, and an empty list means no match rather than no memory.

Input parameters:

- `compact` (boolean): Return trimmed records (id, title, snippet) instead of full bodies. Saves tokens when you only need to know whether something exists.
- `limit` (integer): Maximum number of memories to return. Omit for the server default.
- `query` (string, required): Natural-language search text, e.g. 'what did we decide about the pricing page'. Ranked by how much of it the entry's words and character bigrams cover, plus a small recency nudge and a bonus when the…
- `vaults` (array): Narrow the search to these vault names. Omit to search every vault this agent may read. Naming a vault the agent may not read is not an error - it returns nothing from that vault.

### `propose` (~234 tokens)

Propose a memory

Submit a memory for the human to approve. It lands in a pending queue and changes no confirmed memory. Use it when the human says to remember something, or when a decision is reached that will still matter later. Do not use it as a scratchpad for transient reasoning or for data you merely fetched. This tool cannot confirm its own writes: the entry stays pending until the human accepts it inside their own Hive, so a success response means queued, not stored. Supply client_id to make retries idempotent.

Input parameters:

- `client_id` (string): Idempotency key. Submitting twice with the same key does not create a duplicate - use this when retrying after a timeout.
- `content` (string, required): The memory to store, written as a standalone fact that still makes sense without this conversation - include the who and the when.
- `tags` (array): Free-form tags for later filtering.
- `title` (string): Short label shown in the human's pending queue. Helps them decide quickly.
- `vault` (string): Target vault name. Private vaults are rejected for cloud agents; local agents may target them.

### `manage` (~157 tokens)

Manage stored memories

Inspect or change the lifecycle of a specific stored memory, addressed by id or by queue state. Use list_pending to review what is awaiting the human's approval, and get_by_id to read one entry in full. forget soft-deletes and is reversible with restore; discard_pending permanently drops an entry that was never confirmed. To search confirmed memory by topic instead of by address, use recall. Except for discard_pending, every action here is reversible, which is why this is not marked destructive.

Input parameters:

- `action` (string, required): Which lifecycle operation to run. list_pending takes no id; the other four require one.
- `id` (string): Target memory id. Required for forget, restore, get_by_id and discard_pending; ignored by list_pending.

### `get_context` (~128 tokens)

Get session context

Pull a short digest of recent memory from the human's active threads and open tasks, to seed a conversation before they ask anything. Call this once at session start. For answering a specific question, use recall instead, since that searches all confirmed memory rather than only what is recent. For entries still awaiting approval, use manage with action list_pending. Annotations already declare this read-only; what they cannot say is that the digest reflects the most recent activity, so two calls minutes apart may differ.

Input parameters:

- `limit` (integer): Maximum number of context entries to return. Omit for the server default.

### `say` (~296 tokens)

Post to the shared board

Post a message to the shared board so the human and other agents see what was done or what is being handed over. Use it when finishing a unit of work, or to hand work to another agent. Do not use it to report routine steps the human did not ask about - the human reads this board. To read what others have posted, use board. Identity comes from your credential, so a caller cannot post as another agent.

Input parameters:

- `kind` (string): Card type. May be omitted when stage is given, in which case the kind is derived from the stage.
- `refs` (array): References the reader may want: file paths, commit shas, or memory ids.
- `stage` (string): Work event: starting, handing off, finished, or blocked. Prefixes the body so the board can be filtered and de-duplicated.
- `summary` (string, required): What happened, in one or two sentences. Write the outcome, not a log of steps.
- `task_id` (string): Link this message to an existing task; the hand-off graph aggregates by it.
- `to` (string): Who should see it: 'master' for the human (default), or another agent's id.
- `ttl` (integer): Seconds after which the message stops being returned by board. Defaults to 24 hours, and is clamped to between 60 seconds and 30 days so no card is immortal.

### `board` (~151 tokens)

Read the shared board

Read the shared board, optionally only what arrived since your last read. Use it to poll for messages or hand-offs addressed to you. To post, use say. Pass the previous cursor as since so a poll returns only new messages instead of the whole board. Annotations declare this read-only; note that messages expire, so an empty result can mean nothing was posted or that earlier messages have aged out.

Input parameters:

- `limit` (integer): Maximum number of messages to return. Omit for the server default.
- `roster` (boolean): Also return which agents are currently on duty.
- `since` (string): Cursor from a previous call. Only messages newer than this cursor are returned; omit to read the current board.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/330899935-hive-memory/memory-hive-mcp#diagnostics

## Score history

- 2026-11-04: 62
- 2026-11-03: 62
- 2026-11-02: 61
- 2026-11-01: 76
- 2026-10-31: 75
- 2026-10-30: 60
- 2026-10-29: 59
- 2026-10-28: 74
- 2026-10-27: 74
- 2026-10-26: 63
- 2026-10-25: 78
- 2026-10-24: 77
- 2026-10-23: 77
- 2026-10-22: 62
- 2026-10-21: 39

## Common questions

### What is the Memory Hive MCP server?

Memory Hive is an MCP server listed in the public MCP registry as io.github.330899935/hive-memory. Local-first memory over MCP. Built-in SQLite store; runs standalone. Agents propose; you confirm. This page covers its PyPI package (memory-hive-mcp).

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

Memory Hive scores 62 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 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 Hive MCP server expose?

Memory Hive exposes 6 tools: recall, propose, manage, get_context, say, board. Their descriptions and schemas cost roughly 1,276 tokens of context every time the server is loaded.

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

Memory Hive is still listed as active in the MCP registry. We last reached this channel on 4 November 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 Hive MCP server under?

Memory Hive 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-hive-mcp/
- Socket report: https://socket.dev/pypi/package/memory-hive-mcp
- Website: https://hello-fengchao.com/
- Changelog RSS feed: https://verifymcp.io/servers/330899935-hive-memory/memory-hive-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/330899935-hive-memory/memory-hive-mcp.json
- HTML version of this page: https://verifymcp.io/servers/330899935-hive-memory/memory-hive-mcp