Atlas / MCP servers / pnmcguire480 / cairntir

cairntirCAUTION

mcp/pnmcguire480/cairntir

Local-first persistent memory MCP server for Claude Code, Codex, Cursor, Qwen Code, and AI coding agents. Cross-session, cross-agent SQLite memory.

Verdict
CAUTION
Grade
B
Trust score
89 /100
Exposed tools
4 3r · 1w · 0d
Transport
stdio
License
MIT
Stars
5
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Persistent, local-first memory for AI coding agents. Claude Code, Codex, Cursor, Qwen Code, and other MCP clients share one searchable project history.

[](https://pypi.org/project/cairntir/) [](https://github.com/pnmcguire480/cairntir/actions/workflows/ci.yml) [](https://www.python.org/downloads/) [](LICENSE)

Cairntir stores decisions, facts, unfinished work, and outcomes as verbatim drawers in a SQLite database you own. A budgeted handoff restores complete drawers across sessions; semantic and file-anchored recall find deeper evidence.

Current release: 1.12.3. See the release evidence and changelog. Published downloads are on PyPI and GitHub Releases.

Install

pip install --upgrade cairntir
cairntir setup

Python 3.11+ is required. Setup initializes the store and configures supported hosts it detects. Restart your agent afterward.

cairntir version
cairntir doctor

The diagnostic changes below are unreleased; pip install currently selects published 1.12.3. That release's doctor/status/version may still run registration and update callbacks, and status may open the store for writing. See the change record before treating an installed diagnostic as read-only.

In this candidate, version reports this CLI's version. status and doctor inspect the store and configuration without registering hosts or checking for updates. A configured MCP entry does not prove a live connection. Setup's local write/read check does not prove host delivery or semantic retrieval: require an actual save receipt, then recover the exact task in a fresh

Read from source at commit ac3c74d2360dOBSERVED · 2026-10-11
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add cairntir -- uvx cairntir
claude-desktop
{
  "mcpServers": {
    "cairntir": {
      "command": "uvx",
      "args": [
        "cairntir"
      ]
    }
  }
}
03

Exposed tools (4)

3 read · 1 write · 0 destructive.

ToolRiskDescription
cairntir_auditwriteRun the Quality skill over a wing.
cairntir_cruciblereadStress-test a claim with the Crucible skill.
cairntir_discoveriesreadList the current leaves of the append-only Discovery Ledger.
cairntir_timelinereadChronological view of drawers in a wing mentioning an entity.
04

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeWARN
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
declared (6 observation(s))
Shell
none-observed
Dependencies
pinned
Secrets in source
found

Findings (7)

MEDIUMInventory / provenance · inv.binary · CWE-1104
plans/portable-v2-v6.fixture
portable-v2-v6.fixture
Why it matters. a compiled or binary member cannot be reviewed from source
Fix. ship source, or explain the binary in the README
MEDIUMNetwork egress · net.beacon_words · CWE-200, CWE-319
src/cairntir/prompt_safety.py:41
r"\b(reveal|print|return|exfiltrate)\b.{0,30}"
MEDIUMHard-coded secrets · secret.generic · CWE-798, CWE-321
tests/unit/test_context_acceptance.py:44
SECRET = "confidential-foundation-canary-9db2"  # noqa: S105
LOWInventory / provenance · inv.hidden_file · CWE-1104
.pre-commit-config.yaml
.pre-commit-config.yaml
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
tests/unit/test_ollama_proposer.py:97
proposer = OllamaProposer(model="m", endpoint="http://10.0.0.5:9999/")
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
tests/unit/test_ollama_proposer.py:99
assert captured == ["http://10.0.0.5:9999/api/generate"]
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
lineage/brainstormer/HARNESS_AUDIT.md:44
**Risk:** The entire tiering model is decorative. Any user on community tier has full access to all features. If monetization is ever needed, every command would need retrofit gating.

Gates applied: no_behavioural_pass.

Audited 2026-10-11 · audit v0.4.1 · source sha ac3c74d2360dfull audit observations/trust-audit/mcp-server/pnmcguire480__cairntir.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-11ac3c74d2360dCAUTIONB89first audit
06

Questions

What is the cairntir MCP server?

Local-first persistent memory MCP server for Claude Code, Codex, Cursor, Qwen Code, and AI coding agents. Cross-session, cross-agent SQLite memory.

What tools does cairntir expose?

4 in total: 3 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is cairntir safe to connect to an agent?

With care. The audit graded it B (89/100) and found 7 things worth knowing before you trust this server, listed below with the exact line each was found on.

What credentials does cairntir need?

No credential environment variables were found in its source, so it appears to need none.

How does cairntir run?

It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as cairntir.

How current is this page?

The grade is for one exact copy of the source (ac3c74d2360d), read on 2026-10-11. The repository is watched and re-audited when it changes.

Advertisement