Is Audrey safe and trustworthy?

tashan scores Audrey on public evidence — tashan score 48.0/100, it is currently active, note: a single primary maintainer (bus-factor risk), no known advisories against the current release, its declared dependencies reach: database. Audit scope: OSV advisories, install-time scripts, build provenance and declared permission surface. We do not review source code or execute the capability.

How do I install Audrey?

In Claude Code: run `claude mcp add audrey -- npx -y audrey`. In Cursor / Claude Desktop, add it to mcp.json / claude_desktop_config.json.

‹ The Index

Audrey

npm

Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.

Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code (installable)
installable: each client documents how to load an MCP server of this type — that is the client's promise, not a claim verified against this capability

Category: Security — see all ranked ›

Work: Knowledge management · Agent development

Who it is for: Operations · Researcher · AI engineer

Install (Claude Code):

claude mcp add audrey -- npx -y audrey

deep

“Says at-rest encryption and retention remain deployment responsibilities, not features.”

This grade is wrong ›

tashan score: 48.0
Instruction depth: 85.0 (deep — documents every tool, with worked examples, setup and a stated limitation)
Adoption: 73/wk
Upkeep: 65.0
Freshness: 80.0
Evidence coverage: 100% of the inputs this score can use
Health: active
License: MIT

Security audit

Every finding is shown in full — which advisory, the version that fixes it, and the exact command run at install time. Nothing in this audit is behind a licence.

No known advisoriesclearchecked against OSV for 1.3.0 — this package, not its dependency tree

Connects to databasesfrom declared dependencies

Signed build provenancepublished from public CI with an attestation

What changed recently

2026-08-10 the tashan score for audrey fell to 52.0, from 57.0 Upkeep, freshness or adoption moved enough to change how this measures.
2026-08-23 audrey published 1.2.2, was 1.1.3 A new release is available.
2026-09-13 audrey published 1.3.0, was 1.2.2 A new release is available.

You are reading this because you came looking. tashan Pro gives tashan doctor the history behind it, so a run over your own config says which of YOURS moved.

You searched for one. Check the rest of your stack:

npx tashan-cli doctor

Reads the config already on your machine and names what is dead, deprecated or running code at install time. No account, nothing uploaded.

tashan Pro$6/mo

We recorded 3 changes to Audrey in the last 45 days. Pro tells you on the day — for the servers in your own config, not the ones you thought to look up.

The whole series behind any row, back to the first day we measured it
The replacement, named — not just the news that something died
tashan doctor over your own config, on your own machine

Start a 7-day trial › Everything measured on this page stays free.

Show your score

Measured this well? Put the live badge in your README — it updates as the score does.

[![tashan](https://tashan.sh/badge/pkg-audrey.svg)](https://tashan.sh/capability/pkg-audrey.html)

npm ↗ · source ↗ · pkg:audrey

Already running this? Check your whole config — free, in your browser, nothing installed. Or npx tashan-cli doctor locally, which sends nothing at all.

Measured 2026-09-13 · scorer s5 · how · something wrong here?