# RCLL (npm · fleet-memory-mcp)

Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.

- Trust score: 87/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- npm · `fleet-memory-mcp`: 87/100 (this document), [markdown](https://verifymcp.io/servers/ai-rcll-fleet-memory/fleet-memory-mcp.md), [page](https://verifymcp.io/servers/ai-rcll-fleet-memory/fleet-memory-mcp)

## Channel facts

- Registry: `npm`
- Package: `fleet-memory-mcp`
- Version: `0.1.0`
- 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 2026-09-21.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 95 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Holetron-lab/fleet-memory).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 23 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 44/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 702 tokens (~117/item across 6 items; 5 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 80/100
  - Stability observed for 24 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 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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 RCLL MCP server?

RCLL runs locally as an npm package, launched with npx -y fleet-memory-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 ai-rcll-fleet-memory -- npx -y fleet-memory-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "ai-rcll-fleet-memory": {
      "command": "npx",
      "args": [
        "-y",
        "fleet-memory-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "ai-rcll-fleet-memory": {
      "command": "npx",
      "args": [
        "-y",
        "fleet-memory-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add ai-rcll-fleet-memory -- npx -y fleet-memory-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-rcll-fleet-memory --command npx --arg -y --arg fleet-memory-mcp
```

### Hermes

```yaml
mcp_servers:
  ai-rcll-fleet-memory:
    command: "npx"
    args: ["-y", "fleet-memory-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "ai-rcll-fleet-memory": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "fleet-memory-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add ai-rcll-fleet-memory -t stdio -c npx -a -y fleet-memory-mcp
```

### Other

```json
{
  "mcpServers": {
    "ai-rcll-fleet-memory": {
      "command": "npx",
      "args": [
        "-y",
        "fleet-memory-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.

### 2026-09-21 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 84, +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.

### 2026-09-13 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 82, +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.

### 2026-09-08 (score 81, +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.

### 2026-09-06 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (5)

### `memory_retain` (~219 tokens)

Save a fact, observation, or document to long-term memory with automatic room/hall classification. Rooms: auth, pipeline, schema, infrastructure, ui, api, deployment, monitoring, agent, general. Halls: fact, event, decision, preference, discovery, procedure, warning. Layers: L0=Identity (always loaded), L1=Critical, L2=Session (default), L3=Deep.

Input parameters:

- `bank_id` (string): Memory bank ID (default: fleet-main)
- `context` (string): Context label (e.g. "meeting notes", "client call")
- `document_id` (string): Document ID to group related facts
- `hall` (string): Knowledge type (auto-classified if omitted)
- `layer` (string): Priority layer (default: L2)
- `room` (string): Topic room (auto-classified if omitted)
- `tags` (array): Tags for categorization
- `text` (string, required): The text to memorize — a fact, observation, or document content

### `memory_recall` (~138 tokens)

Search long-term memory for relevant facts. Uses semantic search with optional room/hall scoping for significantly improved retrieval accuracy. Supports layer cascade (L0 results always prioritized).

Input parameters:

- `bank_id` (string): Memory bank ID (default: fleet-main)
- `hall`: Filter by hall(s): fact, event, decision, etc.
- `limit` (number): Max results (default: 10)
- `max_layer` (string): Max layer depth to search (default: L3 = all)
- `query` (string, required): What to search for in memory
- `room`: Filter by room(s) — applied before semantic search

### `memory_reflect` (~78 tokens)

Deep reasoning over memory — synthesizes facts, finds patterns, answers complex questions with citations. Use for analysis: "What patterns emerge from recent events?" or "Summarize everything about X."

Input parameters:

- `bank_id` (string): Memory bank ID (default: fleet-main)
- `query` (string, required): Question to reason about over stored memories

### `memory_compress` (~132 tokens)

Create compressed memory summaries (closets) from stored facts. Groups memories by room+hall and creates AI-generated summaries with source pointers. Use when a topic has accumulated many facts.

Input parameters:

- `bank_id` (string): Memory bank ID (default: fleet-main)
- `hall` (string): Knowledge type to compress (e.g. "fact", "decision")
- `min_sources` (number): Min memories needed to create a closet (default: 5)
- `query` (string): Query to guide compression focus
- `room` (string): Topic to compress (e.g. "auth", "pipeline")

### `memory_bridge` (~130 tokens)

Create a cross-bank memory bridge (tunnel) between two related memories in different banks. Relations: same_concept, depends_on, contradicts, extends. Use when concepts in separate banks are related.

Input parameters:

- `confidence` (number): Confidence score 0.0–1.0 (default: 0.8)
- `relation` (string, required): Relationship type
- `source_bank` (string, required): Source bank ID
- `source_memory` (string, required): UUID of the source memory
- `target_bank` (string, required): Target bank ID
- `target_memory` (string, required): UUID of the target memory

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/ai-rcll-fleet-memory/fleet-memory-mcp#diagnostics

## Score history

- 2026-09-21: 87
- 2026-09-20: 86
- 2026-09-19: 86
- 2026-09-18: 85
- 2026-09-17: 85
- 2026-09-16: 84
- 2026-09-15: 84
- 2026-09-14: 83
- 2026-09-13: 83
- 2026-09-12: 82
- 2026-09-11: 82
- 2026-09-10: 81
- 2026-09-09: 81
- 2026-09-08: 81
- 2026-09-07: 80
- 2026-09-06: 80
- 2026-09-05: 79
- 2026-09-04: 75
- 2026-09-03: 75
- 2026-09-02: 75
- 2026-09-01: 75
- 2026-08-31: 75
- 2026-08-30: 75
- 2026-08-29: 75
- 2026-08-28: 75

## Common questions

### What is the RCLL MCP server?

RCLL is an MCP server listed in the public MCP registry as ai.rcll/fleet-memory. Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path. This page covers its npm package (fleet-memory-mcp).

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

RCLL scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 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 RCLL MCP server expose?

RCLL exposes 5 tools: memory_retain, memory_recall, memory_reflect, memory_compress, memory_bridge. Their descriptions and schemas cost roughly 697 tokens of context every time the server is loaded.

### Is the RCLL MCP server still maintained?

RCLL is still listed as active in the MCP registry. We last reached this channel on 21 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 RCLL MCP server under?

RCLL 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/fleet-memory-mcp
- Socket report: https://socket.dev/npm/package/fleet-memory-mcp
- Repository: https://github.com/Holetron-lab/fleet-memory
- Website: https://rcll.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-rcll-fleet-memory/fleet-memory-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-rcll-fleet-memory/fleet-memory-mcp.json
- HTML version of this page: https://verifymcp.io/servers/ai-rcll-fleet-memory/fleet-memory-mcp