# Reverie (npm · @knowall-ai/reverie)

Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search

- Trust score: 84/100 (high trust)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `@knowall-ai/reverie`: 84/100 (this document), [markdown](https://verifymcp.io/servers/ai-knowall-reverie/knowall-ai-reverie.md), [page](https://verifymcp.io/servers/ai-knowall-reverie/knowall-ai-reverie)

## Channel facts

- Registry: `npm`
- Package: `@knowall-ai/reverie`
- Version: `0.5.2`
- 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**: 90/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects sharp 0.34.5, reached via @huggingface/transformers > sharp. A fixed version is available.
  - No install/post-install scripts declared.
  - 58 of 182 dependencies flagged as unhealthy (1 deprecated).
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to knowall-ai/mcp-reverie).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 13 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1022 tokens (~85/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 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**: 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; "delete_memory" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 12 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 Reverie MCP server?

Reverie runs locally as an npm package, launched with npx -y @knowall-ai/reverie. 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 ai-knowall-reverie -- npx -y @knowall-ai/reverie
```

### Cursor

```json
{
  "mcpServers": {
    "ai-knowall-reverie": {
      "command": "npx",
      "args": [
        "-y",
        "@knowall-ai/reverie"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-knowall-reverie": {
      "command": "npx",
      "args": [
        "-y",
        "@knowall-ai/reverie"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-knowall-reverie -- npx -y @knowall-ai/reverie
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "ai-knowall-reverie": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@knowall-ai/reverie"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add ai-knowall-reverie --command npx --arg -y --arg @knowall-ai/reverie
```

### Hermes

```yaml
mcp_servers:
  ai-knowall-reverie:
    command: "npx"
    args: ["-y", "@knowall-ai/reverie"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-knowall-reverie": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@knowall-ai/reverie"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-knowall-reverie -t stdio -c npx -a -y @knowall-ai/reverie
```

### Other

```json
{
  "mcpServers": {
    "ai-knowall-reverie": {
      "command": "npx",
      "args": [
        "-y",
        "@knowall-ai/reverie"
      ]
    }
  }
}
```

## 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 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 82, +5)

- [functional improvement] Stability: unverified → 0.30

### 2026-09-09 (score 77, 0)

- [security regression] GHSA-rgj7-g3m4-5g8c affects this package: high

### 2026-09-07 (score 77, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-06 (score 62)

First indexed and scored.

## MCP tools (12)

### `search_memories` (~274 tokens)

Hybrid keyword + semantic search across the knowledge graph. "Ben Weeks" can also find "Benjamin Weeks" and each result includes _score and _match.

Input parameters:

- `depth` (integer): Relationship depth to include, 0 to 5, defaults to 1
- `include_archived` (boolean): Include memories with status "archived" (excluded by default).
- `label` (string): Filter by memory label
- `limit` (integer): Maximum results to return, 1 to 200, defaults to 10
- `order_by` (string): Sort order such as created_at DESC, name ASC
- `query` (string): Search text to find in any property. Keyword mode matches any word, while semantic mode can surface close meanings and name variants.
- `search_mode` (string): Search mode: hybrid (default), keyword-only, semantic-only, or exact (case-insensitive equality on name/aliases/email: use before creating a memory).
- `similarity_threshold` (number): Semantic similarity threshold, 0 to 1 inclusive, defaults to 0.4.
- `since_date` (string): ISO date string to filter memories created after this date (e.g., "2024-01-01" or "2024-01-01T00:00:00Z")

### `create_memory` (~136 tokens)

Create a new memory in the knowledge graph. Consider that the memory might already exist, so Search → Create → Connect (its important to try and connect memories)

Input parameters:

- `label` (string, required): Memory label: a plain identifier, Capitalised singular by convention (Person, Place, Organization, Project, Event, Topic, Object, Animal, Concept, Meeting, Decision…). Use list_memory_labels first fo…
- `properties` (object, required): Information to store about this memory (use "name" as primary identifier, e.g. {name: "John Smith", age: 30, occupation: "Engineer"})

### `create_connection` (~112 tokens)

Create a connection between two memories (its good to have connected memories)

Input parameters:

- `fromMemoryId` (number, required): ID of the source memory
- `properties` (object): Optional relationship metadata (e.g. {since: "2023-01", role: "Manager", status: "active"})
- `toMemoryId` (number, required): ID of the target memory
- `type` (string, required): Relationship type such as KNOWS, WORKS_ON, LIVES_IN, HAS_SKILL, PARTICIPATES_IN

### `update_memory` (~55 tokens)

Update properties of an existing memory such as adding more detail or make a change when you find out something new

Input parameters:

- `nodeId` (number, required): ID of the memory to update
- `properties` (object, required): Properties to update/add

### `update_connection` (~102 tokens)

Update properties of an existing connection between memories

Input parameters:

- `fromMemoryId` (number, required): ID of the source memory
- `properties` (object, required): Properties to update/add (e.g. {status: "completed", end_date: "2024-01"})
- `toMemoryId` (number, required): ID of the target memory
- `type` (string, required): Relationship type to identify which connection to update (e.g. WORKS_AT, KNOWS, MANAGES)

### `delete_memory` (~44 tokens)

Delete a memory and all its connections (use with caution - this permanently removes the memory and all its connections)

Input parameters:

- `nodeId` (number, required): ID of the memory to delete

### `delete_connection` (~79 tokens)

Delete a specific connection between two memories (use with caution - this permanently removes the relationship)

Input parameters:

- `fromMemoryId` (number, required): ID of the source memory
- `toMemoryId` (number, required): ID of the target memory
- `type` (string, required): Exact relationship type to delete (e.g. WORKS_AT, KNOWS, MANAGES)

### `list_memory_labels` (~50 tokens)

List all unique memory labels currently in use with their counts (useful for getting an overview of the knowledge graph)

Input parameters:

- `include_archived` (boolean): Include labels of archived memories (excluded by default).

### `query_memories` (~55 tokens)

Run a read-only Cypher query and return up to 200 scrubbed rows.

Input parameters:

- `cypher` (string, required): Read-only Cypher to execute.
- `params` (object): Optional parameter map for the Cypher query.

### `memory_stats` (~26 tokens)

Summarize node, relationship, label, embedding, and orphan counts for the graph.

### `dream` (~44 tokens)

Deterministically relabel, merge duplicates, and refresh embeddings, with an optional dry run report.

Input parameters:

- `dry_run` (boolean): If true, report planned changes without writing them.

### `get_guidance` (~45 tokens)

Get help on using the memory tools effectively

Input parameters:

- `topic` (string): Topic: connections, labels, relationships, best-practices, examples, or leave empty for all

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-knowall-reverie/knowall-ai-reverie#diagnostics

## Score history

- 2026-09-20: 84
- 2026-09-19: 83
- 2026-09-18: 83
- 2026-09-17: 83
- 2026-09-16: 82
- 2026-09-15: 82
- 2026-09-14: 77
- 2026-09-13: 77
- 2026-09-12: 77
- 2026-09-11: 77
- 2026-09-10: 77
- 2026-09-09: 77
- 2026-09-08: 77
- 2026-09-07: 77
- 2026-09-06: 62

## Common questions

### What is the Reverie MCP server?

Reverie is an MCP server listed in the public MCP registry as ai.knowall/reverie. Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search. This page covers its npm package (@knowall-ai/reverie).

### Is the Reverie MCP server safe to use?

Reverie scores 84 out of 100 on VerifyMCP. We recorded 2 known advisories against it as of 20 September 2026. It declares no install or post-install scripts. 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 Reverie MCP server expose?

Reverie exposes 12 tools: search_memories, create_memory, create_connection, update_memory, update_connection, and 7 more. Their descriptions and schemas cost roughly 1,022 tokens of context every time the server is loaded.

### Is the Reverie MCP server still maintained?

Reverie 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 Reverie MCP server under?

Reverie 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

- npm package: https://www.npmjs.com/package/@knowall-ai/reverie
- Socket report: https://socket.dev/npm/package/@knowall-ai/reverie
- Repository: https://github.com/knowall-ai/mcp-reverie
- Changelog RSS feed: https://verifymcp.io/servers/ai-knowall-reverie/knowall-ai-reverie.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-knowall-reverie/knowall-ai-reverie.json
- HTML version of this page: https://verifymcp.io/servers/ai-knowall-reverie/knowall-ai-reverie