Skip to main content
SkillTotal

Is Adeu MCP server (PyPI) safe?

What Adeu MCP server (PyPI) does

Adeu is a Python toolkit and MCP server for redlining Microsoft Word documents. It converts DOCX files to CriticMarkup for language models, applies tracked changes and comments, and compares versions. The PyPI author field lists Mikko Korpela and Uzair Ahmed, the license names Dealfluence Oy, and the code lives in dealfluence/adeu. The stdio server reads and writes DOCX files, adeu init adds it to your Claude Desktop configuration, and on Windows it can work in the open Word application through COM. Before installing on Windows, close any document an agent should not read or edit, because a call with no file path acts on the document open in Word.

Partially analyzed - 1 code file not read (1 minified)
Notable — review in context (a capability is not a malicious indicator):
  • Python shell/command execution
  • Python filesystem read
  • Python filesystem write/delete

What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.

Adeu MCP server (PyPI) is an MCP server analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: filesystem read, filesystem write, mcp tools detected and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

adeu 4.0.1

PyPI package · pypi:adeu
LOW
0
/ 100 risk score
Snapshot · scanned Nov 13, 2026 · adeu@4.0.1 · engine 1.1.0 / ruleset 100

Get notified when this component changes

Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Adeu MCP server (PyPI)'s authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
filesystem readfilesystem writemcp tools detectedshell execution

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Tool surface
Tool Usage
Execution authority
Tool Access Control / Direct Tool Access
Filesystem reach
Tool Execution Context

Findings (4)

CapabilityPython shell/command executionnot scored · severity highST-SHELL-PY

The component can run operating-system commands or spawn processes.

git_sha = subprocess.check_output(
                ["git", "rev-parse", "--short", "HEAD"],
                cwd=str(Path(__file__).parent),
                stderr=subprocess.DEVNULL,
                text=True,
            ).strip()
build_ts_raw = subprocess.check_output(
                ["git", "log", "-1", "--format=%ct"],
                cwd=str(Path(__file__).parent),
                stderr=subprocess.DEVNULL,
                text=True,
            ).strip()
subprocess.run(["open", str(p)], check=True)
subprocess.run(["xdg-open", str(p)], check=True)

Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.

Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; avoid shell=True.

CapabilityPython filesystem readnot scored · severity mediumST-FS-PY-READ

The component reads files from disk.

with open(config_path, "r", encoding="utf-8") as f:
and 'name = "adeu"' in (cwd / "pyproject.toml").read_text(encoding="utf-8", errors="ignore")
current_content = config_path.read_text(encoding="utf-8")
raw = path.read_bytes()
with open(path, "rb") as _fh:
with open(path, "rb") as f:
with open(path, "rb") as f:
diff_warnings.extend(collect_media_difference_warnings(args.original.read_bytes(), args.modified.read_bytes()))
data, applied = apply_comparison_edits(args.original.read_bytes(), edits, eff_author)
data = json.loads(cache_file.read_text(encoding="utf-8"))
existing_data = json.loads(cache_file.read_text(encoding="utf-8"))
data = Path(path).read_bytes()
with open(asset_path, "r", encoding="utf-8") as f:
with open(asset_path, "r", encoding="utf-8") as f:
with open(p, "rb") as f:
with open(pyproject, "r", encoding="utf-8") as f:
with open(build_info_path, "r", encoding="utf-8") as f:
with open(file_path, "rb") as f:
with open(input_p, "rb") as f:
with open(input_path, "rb") as f:
with open(baseline_path, "rb") as f:
raw_bytes = p.read_bytes()

Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.

Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.

CapabilityPython filesystem write/deletenot scored · severity mediumST-FS-PY-WRITE

The component writes or deletes files on disk.

shutil.copy2(config_path, backup_path)
with open(config_path, "w", encoding="utf-8") as f:
tmp_file.write_text(content, encoding="utf-8")
out_file.write_bytes(comparison.data)
with open(fd, "w", encoding="utf-8") as f:
with open(dbg_path, "wb") as f:

Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.

Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.

How attackers abuse these capabilities

Interactive labs on the attack class behind the rules above. They show the technique, not anything found in Adeu MCP server (PyPI).

Maintain Adeu MCP server (PyPI)?

Check the next package before your agent installs it

The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →