cairn
Local-first, model-agnostic memory for you and your AI — one plain-text vault on your machine, nothing leaves.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
CairnRemembers
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
cairn_fetchToken-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
cairn_wanderThe 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
cairn_searchRanked hybrid search across the whole vault. Returns
cairn_noteWrite 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 tran…
cairn_orientSession-start context: the most recent compiled PROTOCOL digest plus open items. Call once at the beginning of a session to inherit prior context.
cairn_recentThe 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
cairn_readRead 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
cairn_logsThe 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
CAIRN_MODELCAIRN_SESSIONCLAUDE_SESSION_IDCLAUDE_MODELCAIRN_CAPTURECAIRN_ACCOUNTDeclare, don't detect: set per account, up front.CAIRN_PROJECTOPENAI_MODELMODEL_NAMECAIRN_CODEX_DEBUGCAIRN_STABLE_PLACESCAIRN_NO_REDACTCAIRN_HARNESSHF_HUB_CACHEHF_HOMEHF_HUB_OFFLINETRANSFORMERS_OFFLINECAIRN_ONNX_MODEL_PATHCAIRN_GPU_DEVICECAIRN_EMBED_BACKENDTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
8/8 tools missing one or more hints — cairn_fetch (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); cairn_wander (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); cairn_search (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +5 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool test coverage
3/8 tools referenced in tests (38%)
Write tests that reference each tool by name so every tool has at least one test.
No eval / new Function
1 eval() or new Function() call — dynamic code execution
Replace eval / Function with explicit parsing or safer alternatives.
Readable source code
1 file are minified or bundled, which is usually build output rather than concealment
Ship unminified, readable source.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/cairnremembers/cairn)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check