# Cairn Remembers (pypi · cairn-remembers)

Local memory your AI tools share: decisions, notes and corrections that carry across sessions.

- Trust score: 63/100 (medium)
- Change this week: −15
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `cairn-remembers`: 63/100 (this document), [markdown](https://verifymcp.io/servers/cairnremembers-cairn-remembers/cairn-remembers.md), [page](https://verifymcp.io/servers/cairnremembers-cairn-remembers/cairn-remembers)

## Channel facts

- Registry: `pypi`
- Package: `cairn-remembers`
- Version: `0.3.4`
- 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 2026-11-05.

- **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.
  - 0 of 1 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: the license (BUSL-1.1) isn't a recognized OSI-approved license.
  - Actively maintained (last published 41 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 885 tokens (~110/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 63% 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 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**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

## Install

### How do I install the Cairn Remembers MCP server?

Cairn Remembers runs locally as a PyPI package, launched with uvx cairn-remembers. 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 cairnremembers-cairn-remembers -- uvx cairn-remembers
```

### Cursor

```json
{
  "mcpServers": {
    "cairnremembers-cairn-remembers": {
      "command": "uvx",
      "args": [
        "cairn-remembers"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "cairnremembers-cairn-remembers": {
      "command": "uvx",
      "args": [
        "cairn-remembers"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add cairnremembers-cairn-remembers -- uvx cairn-remembers
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add cairnremembers-cairn-remembers --command uvx --arg cairn-remembers
```

### Hermes

```yaml
mcp_servers:
  cairnremembers-cairn-remembers:
    command: "uvx"
    args: ["cairn-remembers"]
```

### Netclaw

```json
{
  "McpServers": {
    "cairnremembers-cairn-remembers": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "cairn-remembers"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add cairnremembers-cairn-remembers -t stdio -c uvx -a cairn-remembers
```

### Other

```json
{
  "mcpServers": {
    "cairnremembers-cairn-remembers": {
      "command": "uvx",
      "args": [
        "cairn-remembers"
      ]
    }
  }
}
```

## 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.

### 2026-11-05 (score 63, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-01 (score 78, 0)

- [security] Stability: 0.97 → pass

### 2026-10-31 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 77, −1)

- [security regression] Provenance: unverified → fail
- [functional] Stability: pass → 0.93

### 2026-10-28 (score 78, 0)

- [security regression] Provenance: fail → unverified

### 2026-10-24 (score 78, 0)

- [security] Stability: 0.97 → pass

### 2026-10-23 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 77, 0)

- [security regression] Provenance: unverified → fail
- [functional regression] Security disclosure: unverified → fail

## MCP tools (8)

### `cairn_fetch` (~141 tokens)

Token-saving retrieval: ONE query returns a compact context pack of only the memories/files that matter, fitted to a token budget. Call this INSTEAD of re-reading files or scrolling history — it replaces the re-reading tax with a targeted answer. Top hits come back as capped previews (~1800 chars), the rest as gists — cairn_read returns any node's complete text (raise max_chars for very long nodes).

Input parameters:

- `account` (string): optional: only return memories from this account/galaxy (case-insensitive)
- `budget_tokens` (integer): max tokens in the pack
- `query` (string, required): what you need to know

### `cairn_wander` (~139 tokens)

The creative complement to cairn_fetch. Walks the memory graph outward from the query's best hits, preferring WEAK ties that cross topic boundaries — surfaces adjacent ideas and unseen connections (a past project, an old conversation, an idea from a different domain) that similarity search will never return. Use when brainstorming, stuck, or asked for fresh angles. Returns gists — cairn_read pulls any hit in full (raise max_chars for very long nodes).

Input parameters:

- `hops` (integer): how far to wander (1-5)
- `k` (integer)
- `query` (string, required): what you're working on or thinking about

### `cairn_search` (~82 tokens)

Ranked hybrid search across the whole vault. Returns ids + gists + scores (cheap) — an index, not the text. Pass the ids that matter to cairn_read for their full text — raise max_chars for very long nodes (cairn_fetch for a budgeted context pack).

Input parameters:

- `k` (integer)
- `query` (string, required)

### `cairn_note` (~111 tokens)

Write a memory to the vault — ambient capture. Use for decisions, insights, ideas, open items, warnings, procedures discovered while working. The vault remembers across sessions and models. Write the complete salient fact, decision, warning, or open item WITHOUT truncating it — but do not paste transcripts (turns are captured separately). For a large artifact, save the file and note its path and purpose.

Input parameters:

- `kind` (string)
- `tags` (array)
- `text` (string, required)

### `cairn_orient` (~38 tokens)

Session-start context: the most recent compiled PROTOCOL digest plus open items. Call once at the beginning of a session to inherit prior context.

### `cairn_recent` (~59 tokens)

The working set: recent decisions, open items, and warnings across the vault — what's live right now. Returns gists — pass ids to cairn_read for full text (raise max_chars for very long nodes).

Input parameters:

- `limit` (integer)

### `cairn_read` (~153 tokens)

Read specific nodes IN FULL by id — the follow-up to the gists that recent/search/fetch return; this is the verbatim layer (long turns carry their complete text here). Accepts full ids or unambiguous prefixes, up to 8 per call; max_chars dials the per-node body budget. Unlike fetch/search this needs no embeddings, so it reads nodes written moments ago.

Input parameters:

- `ids` (array, required): node ids (or prefixes) to read
- `max_chars` (integer): per-node canonical-body budget in chars (default 24000; total body across ids caps at max(60000, this)) — raise it to pull a very long turn whole, lower it to skim

### `cairn_logs` (~162 tokens)

The LIVE tail of the vault — newest nodes first, ALL kinds including conversation turns, embedded or not. This is how you see what just happened (fetch/search can't see un-embedded nodes until the nightly sleep). Filter by kind, session prefix, or a contains substring; follow up with cairn_read for full text (raise max_chars for very long nodes).

Input parameters:

- `contains` (string): case-insensitive substring to search live text
- `kind` (string): only this kind (e.g. conversation_turn, decision)
- `limit` (integer): rows to return (max 60)
- `session` (string): session id prefix (e.g. codex-)
- `unembedded_only` (boolean): only nodes the nightly embed hasn't reached

## Diagnostics

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

## Score history

- 2026-11-05: 63
- 2026-11-04: 78
- 2026-11-03: 78
- 2026-11-02: 78
- 2026-11-01: 78
- 2026-10-31: 78
- 2026-10-30: 77
- 2026-10-29: 78
- 2026-10-28: 78
- 2026-10-27: 78
- 2026-10-26: 78
- 2026-10-25: 78
- 2026-10-24: 78
- 2026-10-23: 78
- 2026-10-22: 77
- 2026-10-21: 77
- 2026-10-20: 76
- 2026-10-19: 76
- 2026-10-18: 75
- 2026-10-17: 75
- 2026-10-16: 74
- 2026-10-15: 74
- 2026-10-14: 73
- 2026-10-13: 73
- 2026-10-12: 72
- 2026-10-06: 55
- 2026-10-05: 69
- 2026-10-04: 69
- 2026-10-03: 68
- 2026-10-02: 64

## Common questions

### What is the Cairn Remembers MCP server?

Cairn Remembers is an MCP server listed in the public MCP registry as io.github.CairnRemembers/cairn-remembers. Local memory your AI tools share: decisions, notes and corrections that carry across sessions. This page covers its PyPI package (cairn-remembers).

### Is the Cairn Remembers MCP server safe to use?

Cairn Remembers scores 63 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 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 Cairn Remembers MCP server expose?

Cairn Remembers exposes 8 tools: cairn_fetch, cairn_wander, cairn_search, cairn_note, cairn_orient, and 3 more. Their descriptions and schemas cost roughly 885 tokens of context every time the server is loaded.

### Is the Cairn Remembers MCP server still maintained?

Cairn Remembers is still listed as active in the MCP registry. We last reached this channel on 5 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 Cairn Remembers MCP server under?

Cairn Remembers declares the BUSL-1.1 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

## Links

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