Grades are a hygiene check, not a security guarantee.

MCP, MCP server

com.mnemopay/sdk

The governance layer for AI agents that handle money. Charter-driven mission scope, FiscalGate budget enforcement, EU AI Act Article 12 audit bundles, Agent Reputation Scoring (300-850), and a tamper-evident MerkleAudit chain — across every payment rail an agent will ever to

Compatibility: Not stated.

Grade B

Minor issues only, no Medium or High. Worth a quick look at the findings below before installing.

Graded by PlugVetRubric v2

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

Rescanned at commit c640d57aa191, unchanged since the check below.

NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST SECRETS_PATH_DOTENV PERMISSION_SHELL_DECLARED SECRETS_ENV_READ OBFUSCATION_FILE_OVER_READ_CAP

Why this grade

  • NETWORK_NO_FIXED_HOST Low

    Makes a network call whose host is not written as a fixed address.

    benchmark/longmemeval/evaluate-azure-openai.ts, line 215 const res = await fetch(url, {

  • NETWORK_UNNAMED_HOST Low

    Calls a fixed host that the description does not name.

    benchmark/longmemeval/evaluate-azure-openai.ts, line 215 const res = await fetch(url, {

  • SECRETS_PATH_DOTENV Low

    Mentions a .env file.

    benchmark/longmemeval/ablate.sh, line 17 source ../../.env

  • PERMISSION_SHELL_DECLARED Note

    Runs shell commands, and the manifest or description says so.

    integrations/_shared/mcp_client.py, line 33 self._process: Optional[subprocess.Popen] = None

  • SECRETS_ENV_READ Note

    Reads an environment variable whose name contains KEY, SECRET, TOKEN, PASSWORD or CREDENTIAL.

    benchmark/longmemeval/evaluate-azure-openai.ts, line 106 openaiApiKey: embeddings === "openai" ? (process.env.OPENAI_API_KEY || "") : undefined,

  • OBFUSCATION_FILE_OVER_READ_CAP Note

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

    benchmark/longmemeval/results/recall_only_2026-04-11T03-45-57/details.json, line 1 [

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.

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

    Note

    requests shell access. The manifest names this permission.

    PERMISSION_SHELL_DECLARED

    integrations/_shared/mcp_client.py, line 33

    self._process: Optional[subprocess.Popen] = None

    integrations/_shared/mcp_client.py, line 137

    self._process = subprocess.Popen(

    integrations/agno/mnemopay_agno.py, line 29

    self._process: subprocess.Popen | None = None

    Show more

    integrations/agno/mnemopay_agno.py, line 64

    self._process = subprocess.Popen(

    integrations/autogen/mnemopay_autogen.py, line 32

    self._process: subprocess.Popen | None = None

    integrations/autogen/mnemopay_autogen.py, line 67

    self._process = subprocess.Popen(

    integrations/composio/mnemopay_composio.py, line 37

    self._process: subprocess.Popen | None = None

    integrations/composio/mnemopay_composio.py, line 72

    self._process = subprocess.Popen(

  • Install and update

    Pass

    No install-time script found, and dependencies are pinned or absent.

  • Network

    Concern

    can reach a host that is not written as a fixed address. can reach api.groq.com. The description does not name that host. can reach api.anthropic.com. The description does not name that host. can reach api.openai.com. The description does not name that host.

    NETWORK_NO_FIXED_HOST NETWORK_UNNAMED_HOST

    benchmark/longmemeval/evaluate-azure-openai.ts, line 215

    const res = await fetch(url, {

    benchmark/longmemeval/evaluate-gemini.ts, line 163

    const response = await fetch(url, {

    benchmark/longmemeval/evaluate-groq.ts, line 177

    const response = await fetch("https://api.groq.com/openai/v1/chat/completions", {

    Show more

    benchmark/longmemeval/scripts/download-data.sh, line 29

    if command -v curl &>/dev/null; then

    benchmark/longmemeval/scripts/download-data.sh, line 30

    curl -L --progress-bar -o "$dest" "$url"

    benchmark/longmemeval/scripts/download-data.sh, line 31

    elif command -v wget &>/dev/null; then

    benchmark/longmemeval/scripts/download-data.sh, line 32

    wget --show-progress -q -O "$dest" "$url"

    benchmark/longmemeval/scripts/download-data.sh, line 34

    echo "ERROR: Neither curl nor wget found. Install one and retry."

  • Secrets

    Concern

    reads a credential or environment file.

    SECRETS_ENV_READ SECRETS_PATH_DOTENV

    benchmark/longmemeval/ablate.sh, line 17

    source ../../.env

    benchmark/longmemeval/evaluate-azure-openai.ts, line 106

    openaiApiKey: embeddings === "openai" ? (process.env.OPENAI_API_KEY || "") : undefined,

    benchmark/longmemeval/evaluate-azure-openai.ts, line 256

    const apiKey = process.env.AZURE_OPENAI_KEY || "";

    Show more

    benchmark/longmemeval/evaluate-gemini.ts, line 201

    const apiKey = process.env.GEMINI_API_KEY;

    benchmark/longmemeval/evaluate-groq.ts, line 256

    const apiKey = process.env.GROQ_API_KEY;

    benchmark/longmemeval/evaluate.ts, line 397

    const apiKey = process.env.ANTHROPIC_API_KEY;

    benchmark/longmemeval/evaluate.ts, line 468

    ? process.env.GROQ_API_KEY ?? ""

    benchmark/longmemeval/evaluate.ts, line 470

    ? process.env.OPENAI_API_KEY ?? ""

    benchmark/longmemeval/raw_judge_probe.py, line 7

    _groq_key = os.environ.get("GROQ_API_KEY") or os.environ.get("OPENAI_API_KEY")

    benchmark/longmemeval/validate_fix.sh, line 14

    source ../../.env

    .dockerignore, line 6

    .git

    .dockerignore, line 7

    .env

    .dockerignore, line 9

    **/.env

    .dockerignore, line 10

    **/.env.*

    .env.example, line 2

    # Copy this to .env and fill in your keys. NEVER commit .env to git.

    .gitignore, line 3

    *.tsbuildinfo

  • Agent instructions

    Pass

    No instruction to ignore earlier instructions or to hide a step.

  • Obfuscation

    Note

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

    OBFUSCATION_FILE_OVER_READ_CAP

    benchmark/longmemeval/results/recall_only_2026-04-11T03-45-57/details.json, line 1

    [

  • Licence

    Pass

    A licence file is present (LICENSE).

  • Maintainer activity

    Pass

    The latest commit is within the last 365 days.

Note

Hygiene check of commit c640d57aa191. requests shell access. The manifest names this permission. can reach a host that is not written as a fixed address. can reach api.groq.com. The description does not name that host. can reach api.anthropic.com. The description does not name that host. can reach api.openai.com. The description does not name that host. reads a credential or environment file. a file was over the read cap and was not fully read.

Date and source

Date checked:

View source

github.com

Commit graded: c640d57aa191567a89d12b0dfef9fd7c73fe6580

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