Grades are a hygiene check, not a security guarantee.

MCP, MCP server

recallnest

recallnest, an MCP server listed in the PlugVet directory.

Compatibility: Not stated.

Grade D

Two or more Medium findings, or a High. Only try it in a sandbox.

Graded by PlugVetRubric v2

Not a guarantee. A hygiene check of the source at the commit shown, not a security audit.

Pattern found, check before installing

The checks matched a pattern that needs a closer look. It does not mean the code is harmful. Read the quoted lines below.

  • AGENT_HIDDEN_STEP High

    instruction in an agent instruction file without defensive wording

AGENT_HIDDEN_STEP INSTALL_REMOTE_SCRIPT

Why this grade

  • AGENT_HIDDEN_STEP High

    Text tells the agent to hide a step or not to tell the user.

    SKILL.md, line 231 5. **Silent memory operations.** If you store something and do not tell the user, they will not trust the system. Always confirm.

  • INSTALL_REMOTE_SCRIPT Medium

    Fetches a script from the network and runs it (a pipe to a shell, or an install hook with a URL).

    bin/recallnest.mjs, line 52 curl -fsSL https://bun.sh/install | bash

Any High, or two or more Medium findings, give D. One Medium gives C. Low findings or a security Note give B. Each code names a finding behind the letter.

If you think this grade is wrong, email [email protected] with the entry link and your evidence. We aim to acknowledge within two working days and decide within seven. If we confirm an error, we aim to correct it within 24 hours of confirming it. These are aims, not guarantees.

Grades are a hygiene check of the source at the commit shown, on the date checked, not a security audit or a guarantee. The free directory grades are automated. Before release, a PlugVet engineer reviews every paid report and any grade we hold back, including all F grades, against the source code and the evidence we quote.

What was checked

Plain notes from the hygiene checks.

  • Permissions

    Pass

    No shell or command execution found, and no extra permission was declared.

  • Install and update

    Serious

    install fetches a script from the network.

    INSTALL_REMOTE_SCRIPT

    bin/recallnest.mjs, line 52

    curl -fsSL https://bun.sh/install | bash

    package.json, line 43

    @lancedb/lancedb

  • Network

    Concern

    can reach a host that is not written as a fixed address.

    NETWORK_NO_FIXED_HOST

    assets/ui/app.js, line 66

    const response = await fetch(path, {

    assets/ui/app.js, line 699

    const res = await fetch(`/api/timeline?${qs.toString()}`);

    assets/ui/app.js, line 1137

    fetch('/api/dashboard-stats'),

    Show more

    assets/ui/app.js, line 1138

    fetch('/api/lint-summary'),

    assets/ui/app.js, line 1139

    fetch('/api/stale-memories'),

    integrations/examples/claude-agent-sdk/memory-agent.ts, line 83

    const res = await fetch(`${RECALLNEST}/v1/auto-recall`, {

    integrations/examples/claude-agent-sdk/memory-agent.ts, line 105

    const res = await fetch(`${RECALLNEST}/v1/store`, {

    integrations/examples/langchain/memory-chain.py, line 40

    r = httpx.post(

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    daily-recall.sh, line 21

    # Load .env (JINA_API_KEY, etc.)

    daily-recall.sh, line 22

    if [ -f "$SCRIPT_DIR/.env" ]; then

    daily-recall.sh, line 24

    source "$SCRIPT_DIR/.env"

    Show more

    scripts/incremental-ingest.sh, line 8

    # Load API key from .env (CLI also reads .env, this is for LaunchAgent)

    scripts/incremental-ingest.sh, line 9

    if [ -f "$SCRIPT_DIR/.env" ]; then

    scripts/incremental-ingest.sh, line 11

    source "$SCRIPT_DIR/.env"

    scripts/pull-claude-desktop.ts, line 341

    process.env.CLAUDE_SESSION_KEY ||

    scripts/pull-claude-desktop.ts, line 342

    process.env.CLAUDE_DESKTOP_SESSION_KEY;

    src/cli.ts, line 1343

    console.error(" → 检查 .env 中的 JINA_API_KEY 是否正确");

    src/doctor.ts, line 6

    * 2. .env file + JINA_API_KEY set

    src/doctor.ts, line 324

    const jinaKey = process.env.JINA_API_KEY;

  • Agent instructions

    Serious

    instructions tell the agent to hide a step.

    AGENT_HIDDEN_STEP

    SKILL.md, line 231

    5. **Silent memory operations.** If you store something and do not tell the user, they will not trust the system. Always confirm.

  • Obfuscation

    Note

    a file was over the read cap and was not fully read.

    OBFUSCATION_FILE_OVER_READ_CAP

    scripts/viz-dashboard.html, line 1

    <!DOCTYPE html>

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Get the full report on this tool, £49

Note

Hygiene check of commit e78f8073d6b6. install fetches a script from the network. can reach a host that is not written as a fixed address. reads a credential or environment file. instructions tell the agent to hide a step. a file was over the read cap and was not fully read.

Date and source

Date checked:

View source

github.com

Commit graded: e78f8073d6b61f89a75692c98decacbeca0d30be

This link goes to the original host. PlugVet does not host or check what you download from there, and installing it is your own decision and risk.

Read how this letter is chosen